DeepLearning Note
SoA
- 2017.06.12. Attention Is All You Need: https://arxiv.org/abs/1706.03762
- 2019.02.14. GPT-2, Better Language Models and Their Implications: https://openai.com/blog/better-language-models
- 2020.06.11. GPT-3, OpenAI API: https://openai.com/blog/openai-api
- 2021.01.05. DALL·E: Creating Images from Text: https://openai.com/blog/dall-e
- 2021.06.29. Introducing GitHub Copilot: your AI pair programmer: link
- 2021.08.10. OpenAI Codex: https://openai.com/blog/openai-codex
- 2021.10.29. Solving Math Word Problems: https://openai.com/blog/grade-school-math
- 2021.12.31. A Neural Network Solves and Generates Mathematics Problems by Program Synthesis: https://arxiv.org/abs/2112.15594
- 2022.02.02. Solving (Some) Formal Math Olympiad Problems: https://openai.com/blog/formal-math
- 2022.02.02. Competitive programming with AlphaCode:https://deepmind.com/blog/article/Competitive-programming-with-AlphaCode?fbclid=IwAR1E9sSTt3XiEXn70d2YO8bx8ruBNKArzLhJ8WuZwpclXCK58qihhzgjeVE
AI for Time Series
Main Recent Update Note
- [Jul. 05, 2023] Add papers accepted by KDD'23!
- [Jun. 20, 2023] Add papers accepted by ICML'23!
- [Feb. 07, 2023] Add papers accepted by ICLR'23 and AAAI'23!
- [Sep. 18, 2022] Add papers accepted by NeurIPS'22!
- [Jul. 14, 2022] Add papers accepted by KDD'22!
- [Jun. 02, 2022] Add papers accepted by ICML'22, ICLR'22, AAAI'22, IJCAI'22!
Table of Contents
Tutorials and Surveys
Tutorials
- Robust Time Series Analysis and Applications: An Industrial Perspective, in KDD 2022. [Link]
- Time Series in Healthcare: Challenges and Solutions, in AAAI 2022. [Link]
- Time Series Anomaly Detection: Tools, Techniques and Tricks, in DASFAA 2022. [Link]
- Modern Aspects of Big Time Series Forecasting, in IJCAI 2021. [Link]
- Explainable AI for Societal Event Predictions: Foundations, Methods, and Applications, in AAAI 2021. [Link]
- Physics-Guided AI for Large-Scale Spatiotemporal Data, in KDD 2021. [Link]
- Deep Learning for Anomaly Detection, in KDD & WSDM 2020. [Link1] [Link2] [Link3]
- Building Forecasting Solutions Using Open-Source and Azure Machine Learning, in KDD 2020. [Link]
- Interpreting and Explaining Deep Neural Networks: A Perspective on Time Series Data, KDD 2020. [Link]
- Forecasting Big Time Series: Theory and Practice, KDD 2019. [Link]
- Spatio-Temporal Event Forecasting and Precursor Identification, KDD 2019. [Link]
- Modeling and Applications for Temporal Point Processes, KDD 2019. [Link1] [Link2]
Surveys
General Time Series Survey
- Transformers in Time Series: A Survey, in IJCAI 2023. [paper] [GitHub Repo]
- Time series data augmentation for deep learning: a survey, in IJCAI 2021. [paper]
- Neural temporal point processes: a review, in IJCAI 2021. [paper]
- Causal inference for time series analysis: problems, methods and evaluation, in KAIS 2022. [paper]
- Survey and Evaluation of Causal Discovery Methods for Time Series, in JAIR 2022. [paper]
- Deep learning for spatio-temporal data mining: A survey, in TKDE 2020. [paper]
- Generative Adversarial Networks for Spatio-temporal Data: A Survey, in TIST 2022. [paper]
- Spatio-Temporal Data Mining: A Survey of Problems and Methods, in CSUR 2018. [paper]
- A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series, in NeurIPS Workshop 2020. [paper]
- Count Time-Series Analysis: A signal processing perspective, in SPM 2019. [paper]
- Wavelet transform application for/in non-stationary time-series analysis: a review, in Applied Sciences 2019. [paper]
- Granger Causality: A Review and Recent Advances, in Annual Review of Statistics and Its Application 2014. [paper]
- A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data, in arXiv 2020. [paper]
- Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data, in arXiv 2022. [paper]
- A Survey on Time-Series Pre-Trained Models, in arXiv 2023. [paper] [link]
- Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects, in arXiv 2023. [paper] [Website]
- A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection, in arXiv 2023. [paper] [Website]
Time Series Forecasting Survey
- Forecasting: theory and practice, in IJF 2022. [paper]
- Time-series forecasting with deep learning: a survey, in Philosophical Transactions of the Royal Society A 2021. [paper]
- Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions, in TITS 2022. [paper]
- Event prediction in the big data era: A systematic survey, in CSUR 2022. [paper]
- A brief history of forecasting competitions, in IJF 2020. [paper]
- Neural forecasting: Introduction and literature overview, in arXiv 2020. [paper]
- Probabilistic forecasting, in Annual Review of Statistics and Its Application 2014. [paper]
Time Series Anomaly Detection Survey
- A review on outlier/anomaly detection in time series data, in CSUR 2021. [paper]
- Anomaly detection for IoT time-series data: A survey, in IEEE Internet of Things Journal 2019. [paper]
- A Survey of AIOps Methods for Failure Management, in TIST 2021. [paper]
- Sequential (quickest) change detection: Classical results and new directions, in IEEE Journal on Selected Areas in Information Theory 2021. [paper]
- Outlier detection for temporal data: A survey, TKDE'13. [paper]
- Anomaly detection for discrete sequences: A survey, TKDE'12. [paper]
- Anomaly detection: A survey, CSUR'09. [paper]
Time Series Classification Survey
- Deep learning for time series classification: a review, in Data Mining and Knowledge Discovery 2019. [paper]
- Approaches and Applications of Early Classification of Time Series: A Review, in IEEE Transactions on Artificial Intelligence 2020. [paper]
Papers 2023
NeurIPS 2023
ICML 2023
Time Series Forecasting
- Learning Deep Time-index Models for Time Series Forecasting [paper]
- Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts [paper]
- Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting [paper]
- Feature Programming for Multivariate Time Series Prediction [paper]
- Non-autoregressive Conditional Diffusion Models for Time Series Prediction [paper]
Time Series Anomaly Detection, Classification, Imputation, and XAI
- Prototype-oriented unsupervised anomaly detection for multivariate time series [paper]
- Probabilistic Imputation for Time-series Classification with Missing Data [paper]
- Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation [paper]
- Self-Interpretable Time Series Prediction with Counterfactual Explanations [paper]
- Learning Perturbations to Explain Time Series Predictions [paper]
Other Time Series Analysis
- Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion [paper]
- Neural Stochastic Differential Games for Time-series Analysis [paper]
- Sequential Monte Carlo Learning for Time Series Structure Discovery [paper]
- Context Consistency Regularization for Label Sparsity in Time Series [paper]
- Sequential Predictive Conformal Inference for Time Series [paper]
- Improved Online Conformal Prediction via Strongly Adaptive Online Learning [paper]
- Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series [paper]
- SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series [paper]
- Domain Adaptation for Time Series Under Feature and Label Shifts [paper]
- Deep Latent State Space Models for Time-Series Generation [paper]
- Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series [paper]
- Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting [paper]
- Generalized Teacher Forcing for Learning Chaotic Dynamics [paper]
- Learning the Dynamics of Sparsely Observed Interacting Systems [paper]
- Markovian Gaussian Process Variational Autoencoders [paper]
- ClimaX: A foundation model for weather and climate [paper]
ICLR 2023
Time Series Forecasting
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers [paper] [official code]
- Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting [paper] [official code]
- Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting [paper] [official code]
- MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting [paper] [official code]
- Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting [paper] [official code]
- Learning Fast and Slow for Time Series Forecasting [paper] [official code]
- Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts [paper] [official code]
- Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms [paper] [official code]
Time Series Anomaly Detection and Classification
- Unsupervised Model Selection for Time Series Anomaly Detection [paper] [official code]
- Out-of-distribution Representation Learning for Time Series Classification [paper] [official code]
Other Time Series Analysis
- Effectively Modeling Time Series with Simple Discrete State Spaces [paper] [official code]
- TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis [paper] [official code]
- Contrastive Learning for Unsupervised Domain Adaptation of Time Series [paper] [official code]
- Recursive Time Series Data Augmentation [paper] [official code]
- Multivariate Time-series Imputation with Disentangled Temporal Representations [paper] [official code]
- Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths [paper] [official code]
- Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise [paper] [official code]
- CUTS: Neural Causal Discovery from Unstructured Time-Series Data [paper] [official code]
- Temporal Dependencies in Feature Importance for Time Series Prediction [paper] [official code]
KDD 2023
Time Series Anomaly Detection
- DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection [paper] [official code]
- Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models [paper] [official code]
- Precursor-of-Anomaly Detection for Irregular Time Series [paper]
Time Series Forecasting
- When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
- TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting [paper]
- Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting
- Sparse Binary Transformers for Multivariate Time Series Modeling [paper] [official code]
- Interactive Generalized Additive Model and Its Applications in Electric Load Forecasting
Time Series Forecasting (Traffic)
- Frigate: Frugal Spatio-temporal Forecasting on Road Networks [paper] [official code]
- Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities
- Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training
- Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction
Time Series Imputation
- Source-Free Domain Adaptation with Temporal Imputation for Time Series Data [paper] [official code]
- Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
- An Observed Value Consistent Diffusion Model for Imputing Missing Values in Multivariate Time Series
Others
- Online Few-Shot Time Series Classification for Aftershock Detection [paper] [official code]
- Self-supervised Classification of Clinical Multivariate Time Series using Time Series Dynamics
- Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series
- Parameter-free Spikelet: Discovering Different Length and Warped Time Series Motifs using an Adaptive Time Series Representation
- FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework
- WHEN: A Wavelet-DTW Hybrid Attention Network for Heterogeneous Time Series Analysis
AAAI 2023
Time Series Forecasting
- AirFormer: Predicting Nationwide Air Quality in China with Transformers [paper] [official code]
- Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting [paper] [official code]
- WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series [paper] [official code]
- Are Transformers Effective for Time Series Forecasting [paper] [official code]
- Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose [paper] [official code]
- An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks [paper] [official code]
- Spatio-Temporal Meta-Graph Learning for Traffic Forecasting [paper] [official code]
Other Time Series Analysis
- Temporal-Frequency Co-Training for Time Series Semi-Supervised Learning [paper] [official code]
- SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation [paper] [official code]
- Causal Recurrent Variational Autoencoder for Medical Time Series Generation [paper] [official code]
- AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-series Generation [paper] [official code]
- SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification [paper] [official code]
Papers 2022
NeurIPS 2022
Time Series Forecasting
-
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting [paper] [official code]
-
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction [paper] [official code]
-
Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting [paper]
-
Earthformer: Exploring Space-Time Transformers for Earth System Forecasting [paper]
-
Generative Time Series Forecasting with Diffusion, Denoise and Disentanglement
-
Learning Latent Seasonal-Trend Representations for Time Series Forecasting
-
WaveBound: Dynamically Bounding Error for Stable Time Series Forecasting
-
Time Dimension Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting
-
Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks
-
C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting
-
Meta-Learning Dynamics Forecasting Using Task Inference [paper]
-
Conformal Prediction with Temporal Quantile Adjustments
Other Time Series Analysis
-
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency, [paper] [official code]
-
Causal Disentanglement for Time Series
-
BILCO: An Efficient Algorithm for Joint Alignment of Time Series
-
Dynamic Sparse Network for Time Series Classification: Learning What to “See”
-
AutoST: Towards the Universal Modeling of Spatio-temporal Sequences
-
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
-
Efficient learning of nonlinear prediction models with time-series privileged information
-
Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models
ICML 2022
Time Series Forecasting
- FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting [paper] [official code]
- TACTiS: Transformer-Attentional Copulas for Time Series [paper] [official code]
- Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes [paper] [official code]
- Domain Adaptation for Time Series Forecasting via Attention Sharing [paper]
- DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting [paper] [official code]
Time Series Anomaly Detection
- Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection [paper]
Other Time Series Analysis
- Adaptive Conformal Predictions for Time Series [paper] [official code]
- Modeling Irregular Time Series with Continuous Recurrent Units [paper] [official code]
- Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion [paper]
- Reconstructing nonlinear dynamical systems from multi-modal time series [paper] [official code]
- Utilizing Expert Features for Contrastive Learning of Time-Series Representations [paper] [official code]
- Learning of Cluster-based Feature Importance for Electronic Health Record Time-series [paper]
ICLR 2022
Time Series Forecasting
- Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting [paper] [official code]
- DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting [paper] [official code]
- CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting [paper] [official code]
- Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift [paper] [official code]
- TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting [paper] [official code]
- Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [paper] [official code]
- On the benefits of maximum likelihood estimation for Regression and Forecasting [paper]
- Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting [paper] [official code]
Time Series Anomaly Detection
- Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy [paper] [official code]
- Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series [paper] [official code]
Time Series Classification
- T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis [paper]
- Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification [paper]
Other Time Series Analysis
- Graph-Guided Network for Irregularly Sampled Multivariate Time Series [paper]
- Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series [paper]
- Transformer Embeddings of Irregularly Spaced Events and Their Participants [paper]
- Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks [paper]
- PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series [paper]
- Huber Additive Models for Non-stationary Time Series Analysis [paper]
- LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations [paper]
- Imbedding Deep Neural Networks [paper]
- Coherence-based Label Propagation over Time Series for Accelerated Active Learning [paper]
- Long Expressive Memory for Sequence Modeling [paper]
- Autoregressive Quantile Flows for Predictive Uncertainty Estimation [paper]
- Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks [paper]
- Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification [paper]
- Explaining Point Processes by Learning Interpretable Temporal Logic Rules [paper]
KDD 2022
Time Series Forecasting
- Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting [code]
- Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting
- Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
- Multi-Variate Time Series Forecasting on Variable Subset
- Greykite: Deploying Flexible Forecasting at Scale in LinkedIn
Time Series Anomaly Detection
- Local Evaluation of Time Series Anomaly Detection Algorithms
- Scaling Time Series Anomaly Detection to Trillions of Datapoints and Ultra-fast Arriving Data Streams
Other Time-Series/Spatio-Temporal Analysis
- Task-Aware Reconstruction for Time-Series Transformer
- Towards Learning Disentangled Representations for Time Series
- ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences
- Non-stationary Time-aware Kernelized Attention for Temporal Event Prediction
- MSDR: Multi-Step Dependency Relation Networks for Spatial Temporal Forecasting
- Graph2Route: A Dynamic Spatial-Temporal Graph Neural Network for Pick-up and Delivery Route Prediction
- Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models
- Robust Event Forecasting with Spatiotemporal Confounder Learning
- Mining Spatio-Temporal Relations via Self-Paced Graph Contrastive Learning
- Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
- Characterizing Covid waves via spatio-temporal decomposition
AAAI 2022
Time Series Forecasting
- CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting [paper]
- Reinforcement Learning based Dynamic Model Combination for Time Series Forecasting [paper]
- DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation [paper] official code]
- PrEF: Probabilistic Electricity Forecasting via Copula-Augmented State Space Model [paper]
- LIMREF: Local Interpretable Model Agnostic Rule-Based Explanations for Forecasting, with an Application to Electricity Smart Meter Data [paper]
- Learning and Dynamical Models for Sub-Seasonal Climate Forecasting: Comparison and Collaboration [paper] [official code]
- CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting [paper]
- Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting [paper] [official code]
- Graph Neural Controlled Differential Equations for Traffic Forecasting [paper] [official code]
- STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction [paper] [official code]
Time Series Anomaly Detection
- Towards a Rigorous Evaluation of Time-Series Anomaly Detection [paper]
- AnomalyKiTS-Anomaly Detection Toolkit for Time Series [Demo paper]
Other Time Series Analysis
- TS2Vec: Towards Universal Representation of Time Series [paper] [official code]
- I-SEA: Importance Sampling and Expected Alignment-Based Deep Distance Metric Learning for Time Series Analysis and Embedding [paper]
- Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis [paper]
- Conditional Loss and Deep Euler Scheme for Time Series Generation [paper]
- Clustering Interval-Censored Time-Series for Disease Phenotyping [paper]
IJCAI 2022
Time Series Forecasting
- Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting [paper]
- Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts [paper] [official code]
- Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
- DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data [paper] [official code]
- Memory Augmented State Space Model for Time Series Forecasting
- Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data
- Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention [paper] [official code]
- FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting
Time Series Anomaly Detection
- Neural Contextual Anomaly Detection for Time Series [paper]
- GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning
Time Series Classification
- A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification [paper]
- T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification
SIGMOD VLDB ICDE 2022
Time Series Forecasting
- METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting, VLDB'22. [paper] [official code]
- AutoCTS: Automated Correlated Time Series Forecasting, VLDB'22. [paper]
- Towards Spatio-Temporal Aware Traffic Time Series Forecasting, ICDE'22. [paper] [official code]
Time Series Anomaly Detection
- Sintel: A Machine Learning Framework to Extract Insights from Signals, SIGMOD'22. [paper] [official code]
- TSB-UAD: An End-to-End Benchmark Suite for Univariate Time-Series Anomaly Detection, VLDB'22. [paper] [official code]
- TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data, VLDB'22. [paper] [official code]
- Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles, VLDB'22. [paper]
- Robust and Explainable Autoencoders for Time Series Outlier Detection, ICDE'22. [paper]
- Anomaly Detection in Time Series with Robust Variational Quasi-Recurrent Autoencoders, ICDE'22.
Time Series Classification
- IPS: Instance Profile for Shapelet Discovery for Time Series Classification, ICDE'22. [paper]
- Towards Backdoor Attack on Deep Learning based Time Series Classification, ICDE'22. [paper]
Other Time Series Analysis
- OnlineSTL: Scaling Time Series Decomposition by 100x, VLDB'22. [paper]
- Efficient temporal pattern mining in big time series using mutual information, VLDB'22. [paper]
- Learning Evolvable Time-series Shapelets, ICDE'22.
Misc 2022
Time Series Forecasting
- CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting, WWW'22. [paper] [official code]
- Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction, WWW'22. [paper]
- RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph, WWW'22. [paper]
- Robust Probabilistic Time Series Forecasting, AISTATS'22. [paper] [official code]
- Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting, AISTATS'22. [paper]
Time Series Anomaly Detection
- TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis, CIKM'22. [paper] [official code]
- Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection, AISTATS'22. [paper] [official code]
- A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems, WWW'22. [paper]
Other Time Series Analysis
- Decoupling Local and Global Representations of Time Series, AISTATS'22. [paper] [official code]
- LIMESegment: Meaningful, Realistic Time Series Explanations, AISTATS'22. [paper]
- Using time-series privileged information for provably efficient learning of prediction models, AISTATS'22. [paper] [official code]
- Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimation, AISTATS'22. [paper] [official code]
- EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting, WWW'22. [paper]
Papers 2021
NeurIPS 2021
Time Series Forecasting
- Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting [paper] [official code]
- MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data [paper]
- Conformal Time-Series Forecasting [paper] [official code]
- Probabilistic Forecasting: A Level-Set Approach [paper]
- Topological Attention for Time Series Forecasting [paper]
- When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [paper] [official code]
- Monash Time Series Forecasting Archive [paper] [official code]
Time Series Anomaly Detection
- Revisiting Time Series Outlier Detection: Definitions and Benchmarks [paper] [official code]
- Online false discovery rate control for anomaly detection in time series [paper]
- Detecting Anomalous Event Sequences with Temporal Point Processes [paper]
Other Time Series Analysis
- Probabilistic Transformer For Time Series Analysis [paper]
- Shifted Chunk Transformer for Spatio-Temporal Representational Learning [paper]
- Deep Explicit Duration Switching Models for Time Series [paper] [official code]
- Time-series Generation by Contrastive Imitation [paper]
- CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation [paper] [official code]
- Adjusting for Autocorrelated Errors in Neural Networks for Time Series [paper] [official code]
- SSMF: Shifting Seasonal Matrix Factorization [paper] [official code]
- Coresets for Time Series Clustering [paper]
- Neural Flows: Efficient Alternative to Neural ODEs [paper] [official code]
- Spatio-Temporal Variational Gaussian Processes [paper] [official code]
- Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers [paper] [official code]
ICML 2021
Time Series Forecasting
- Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting [paper] [official code]
- End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series [paper] [official code]
- RNN with particle flow for probabilistic spatio-temporal forecasting [paper] [official code]
- Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting [paper] [official code]
- Variance Reduction in Training Forecasting Models with Subgroup Sampling [paper]
- Explaining Time Series Predictions With Dynamic Masks [paper] [official code]
- Conformal prediction interval for dynamic time-series [paper] [official code]
Time Series Anomaly Detection
- Neural Transformation Learning for Deep Anomaly Detection Beyond Images [paper] [official code]
- Event Outlier Detection in Continuous Time [paper] [official code]
Other Time Series Analysis
- Voice2Series: Reprogramming Acoustic Models for Time Series Classification [paper] [official code]
- Neural Rough Differential Equations for Long Time Series [paper] [official code]
- Neural Spatio-Temporal Point Processes [paper] [official code]
- Learning Neural Event Functions for Ordinary Differential Equations [paper] [official code]
- Approximation Theory of Convolutional Architectures for Time Series Modelling [paper]
- Whittle Networks: A Deep Likelihood Model for Time Series [paper] [official code]
- Necessary and sufficient conditions for causal feature selection in time series with latent common causes [paper]
ICLR 2021
Time Series Forecasting
- Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows [paper] [official code]
- Discrete Graph Structure Learning for Forecasting Multiple Time Series [paper] [official code]
Other Time Series Analysis
- Clairvoyance: A Pipeline Toolkit for Medical Time Series [paper] [official code]
- Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding [paper] [official code]
- Multi-Time Attention Networks for Irregularly Sampled Time Series [paper] [official code]
- Generative Time-series Modeling with Fourier Flows [paper] [official code]
- Differentiable Segmentation of Sequences [paper] [slides] [official code]
- Neural ODE Processes [paper] [official code]
- Learning Continuous-Time Dynamics by Stochastic Differential Networks [paper] [official code]
KDD 2021
Time Series Forecasting
- ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting [paper] [official code]
- Graph Deep Factors for Forecasting with Applications to Cloud Resource Allocation [paper]
- Quantifying Uncertainty in Deep Spatiotemporal Forecasting [paper]
- Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting [paper] [official code]
- TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction [paper]
- Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting [paper]
Time Series Anomaly Detection
- Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding [paper] [official code]
- Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization [paper] [official code]
- Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering [paper] [official code]
- Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection [paper] [official code]
Other Time Series Analysis
- Representation Learning of Multivariate Time Series using a Transformer Framework [paper] [official code]
- Causal and Interpretable Rules for Time Series Analysis [paper]
- MiniRocket: A Fast (Almost) Deterministic Transform for Time Series Classification [paper] [official code]
- Statistical models coupling allows for complex localmultivariate time series analysis [paper]
- Fast and Accurate Partial Fourier Transform for Time Series Data [paper] [official code]
- Deep Learning Embeddings for Data Series Similarity Search [paper] [link]
AAAI 2021
Time Series Forecasting
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting [paper] [official code]
- Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting [paper] [official code]
- Dynamic Gaussian Mixture Based Deep Generative Model for Robust Forecasting on Sparse Multivariate Time Series [paper] [official code]
- Temporal Latent Autoencoder: A Method for Probabilistic Multivariate Time Series Forecasting [paper]
- Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting [paper]
- Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting [paper]
- Attentive Neural Point Processes for Event Forecasting [paper] [official code]
- Forecasting Reservoir Inflow via Recurrent Neural ODEs [paper]
- Hierarchical Graph Convolution Network for Traffic Forecasting [paper]
- Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network [paper] [official code]
- Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting [paper] [official code]
- FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting [paper] [official code]
- Fairness in Forecasting and Learning Linear Dynamical Systems [paper]
- A Multi-Step-Ahead Markov Conditional Forward Model with Cube Perturbations for Extreme Weather Forecasting [paper]
- Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances [paper]
Time Series Anomaly Detection
- Graph Neural Network-Based Anomaly Detection in Multivariate Time Series [paper] [official code]
- Time Series Anomaly Detection with Multiresolution Ensemble Decoding [paper]
- Outlier Impact Characterization for Time Series Data [paper]
Time Series Classification
- Correlative Channel-Aware Fusion for Multi-View Time Series Classification [paper]
- Learnable Dynamic Temporal Pooling for Time Series Classification [paper] [official code]
- ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification [paper]
- Joint-Label Learning by Dual Augmentation for Time Series Classification [paper]
Other Time Series Analysis
- Time Series Domain Adaptation via Sparse Associative Structure Alignment [paper] [official code]
- Learning Representations for Incomplete Time Series Clustering [paper]
- Generative Semi-Supervised Learning for Multivariate Time Series Imputation [paper] [official code]
- Second Order Techniques for Learning Time-Series with Structural Breaks [paper]
IJCAI 2021
Time Series Forecasting
- Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting [paper]
- Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks [paper]
- Hierarchical Adaptive Temporal-Relational Modeling for Stock Trend Prediction [paper]
- TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning [paper] [official code]
Other Time Series Analysis
- Time Series Data Augmentation for Deep Learning: A Survey [paper]
- Time-Series Representation Learning via Temporal and Contextual Contrasting [paper] [official code]
- Adversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation [paper] [official code]
- Time-Aware Multi-Scale RNNs for Time Series Modeling [paper]
- TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data [paper]
SIGMOD VLDB ICDE 2021
Time Series Forecasting
- AutoAI-TS:AutoAI for Time Series Forecasting, SIGMOD'21. [paper]
- FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data, VLDB'21. [paper]
- MDTP: a multi-source deep traffic prediction framework over spatio-temporal trajectory data, VLDB'21. [paper]
- EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting, ICDE'21. [paper] [slides]
- An Effective Joint Prediction Model for Travel Demands and Traffic Flows, ICDE'21. [paper]
Time Series Anomaly Detection
- Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series, VLDB'21. [paper] [official code]
- SAND: Streaming Subsequence Anomaly Detection, VLDB'21. [paper]
Other Time Series Analysis
- RobustPeriod: Robust Time-Frequency Mining for Multiple Periodicity Detection, SIGMOD'21. [paper] [code]
- ORBITS: Online Recovery of Missing Values in Multiple Time Series Streams, VLDB'21. [paper] [official code]
- Missing Value Imputation on Multidimensional Time Series, VLDB'21. [paper]
Misc 2021
Time Series Forecasting
- DeepFEC: Energy Consumption Prediction under Real-World Driving Conditions for Smart Cities, WWW'21. [paper] [official code]
- AutoSTG: Neural Architecture Search for Predictions of Spatio-Temporal Graph, WWW'21. [paper] [official code]
- REST: Reciprocal Framework for Spatiotemporal-coupled Predictions, WWW'21. [paper]
- Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series, AISTATS'21. [paper]
- SSDNet: State Space Decomposition Neural Network for Time Series Forecasting, ICDM'21. [paper]
- AdaRNN: Adaptive Learning and Forecasting of Time Series, CIKM'21. [paper] [official code]
- Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction, CIKM'21. [paper]
- Stock Trend Prediction with Multi-Granularity Data: A Contrastive Learning Approach with Adaptive Fusion, CIKM'21. [paper]
- DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction, CIKM'21. [paper] [official code1] [official code2]
- Long Horizon Forecasting With Temporal Point Processes, WSDM'21. [paper] [official code]
- Time-Series Event Prediction with Evolutionary State Graph, WSDM'21. [paper] [official code].
Time Series Anomaly Detection
- SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs, WWW'21. [paper]
- Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding, WWW'21. [paper] [official code]
- FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection, WSDM'21. [paper]
- Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping, ICCV'21. [paper] [official code]
- Jump-Starting Multivariate Time Series Anomaly Detection for Online Service Systems, ATC'21. [paper]
Other Time Series Analysis
- Network of Tensor Time Series, WWW'21. [paper] [official code]
- Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series, WWW'21. [paper] [official code]
- SrVARM: State Regularized Vector Autoregressive Model for Joint Learning of Hidden State Transitions and State-Dependent Inter-Variable Dependencies from Multi-variate Time Series, WWW'21. [paper]
- Deep Fourier Kernel for Self-Attentive Point Processes, AISTATS'21. [paper]
- Differentiable Divergences Between Time Series, AISTATS'21. [paper] [official code]
- Aligning Time Series on Incomparable Spaces, AISTATS'21. [paper] [official code]
- Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions, ICDM'21. [paper]
- Towards Generating Real-World Time Series Data, ICDM'21. [paper] [official code]
- Learning Saliency Maps to Explain Deep Time Series Classifiers, CIKM'21. [paper] [official code]
- Actionable Insights in Urban Multivariate Time-series, CIKM'21. [paper]
- Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals, WSDM'21. [paper]
Papers 201X-2020 Selected
NeurIPS 201X-2020
Time Series Forecasting
- Adversarial Sparse Transformer for Time Series Forecasting, NeurIPS'20. [paper] [official code]
- Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting, NeurIPS'20. [paper] [official code]
- Deep Rao-Blackwellised Particle Filters for Time Series Forecasting, NeurIPS'20. [paper]
- Probabilistic Time Series Forecasting with Shape and Temporal Diversity, NeurIPS'20. [paper] [official code]
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting, NeurIPS'20. [paper] [official code]
- Interpretable Sequence Learning for Covid-19 Forecasting, NeurIPS'20. [paper]
- Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting, NeurIPS'19. [paper] [code]
- Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting, NeurIPS'19. [paper] [official code]
- High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes, NeurIPS'19. [paper] [official code]
- Deep State Space Models for Time Series Forecasting, NeurIPS'18. [paper]
- Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction, NeurIPS'16. [paper]
Time Series Anomaly Detection
- Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network, NeurIPS'20. [paper]
- PIDForest: Anomaly Detection via Partial Identification, NeurIPS'19. [paper] [official code]
- Precision and Recall for Time Series, NeurIPS'18. [paper] [official code]
Time Series Classification
- Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices, NeurIPS'19. [paper]
Time Series Clustering
- Learning Representations for Time Series Clustering, NeurIPS'19. [paper] [official code]
- Learning low-dimensional state embeddings and metastable clusters from time series data, NeurIPS'19. [paper]
Time Series Imputation
- NAOMI: Non-autoregressive multiresolution sequence imputation, NeurIPS'19. [paper] [official code]
- BRITS: Bidirectional Recurrent Imputation for Time Series, NeurIPS'18. [paper] [official code]
- Multivariate Time Series Imputation with Generative Adversarial Networks, NeurIPS'18. [paper] [official code]
Time Series Neural xDE
- Neural Controlled Differential Equations for Irregular Time Series, NeurIPS'20. [paper] [official code]
- GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series, NeurIPS'19. [paper] [official code]
- Latent Ordinary Differential Equations for Irregularly-Sampled Time Series, NeurIPS'19. [paper] [official code]
- Neural Ordinary Differential Equations, NeurIPS'18. [paper] [official code]
General Time Series Analysis
- High-recall causal discovery for autocorrelated time series with latent confounders, NeurIPS'20. [paper] [paper2] [official code]
- Benchmarking Deep Learning Interpretability in Time Series Predictions, NeurIPS'20. [paper] [official code]
- What went wrong and when? Instance-wise feature importance for time-series black-box models, NeurIPS'20. [paper] [official code]
- Normalizing Kalman Filters for Multivariate Time Series Analysis, NeurIPS'20. [paper]
- Unsupervised Scalable Representation Learning for Multivariate Time Series, NeurIPS'19. [paper] [official code]
- Time-series Generative Adversarial Networks, NeurIPS'19. [paper] [official code]
- U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging, NeurIPS'19. [paper] [official code]
- Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders, NeurIPS'18. [paper]
- Safe Active Learning for Time-Series Modeling with Gaussian Processes, NeurIPS'18. [paper]
ICML 201X-2020
General Time Series Analysis
- Learning from Irregularly-Sampled Time Series: A Missing Data Perspective, ICML'20. [paper] [official code]
- Set Functions for Time Series, ICML'20. [paper] [official code]
- Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders, ICML'20. [paper] [official code]
- Spectral Subsampling MCMC for Stationary Time Series, ICML'20. [paper]
- Learnable Group Transform For Time-Series, ICML'20. [paper]
- Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models, ICML'19. [paper] [official code]
- Discovering Latent Covariance Structures for Multiple Time Series, ICML'19. [paper]
- Autoregressive convolutional neural networks for asynchronous time series, ICML'18. [paper] [official code]
- Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series, ICML'18. [paper]
- Soft-DTW: a Differentiable Loss Function for Time-Series, ICML'17. [paper] [official code]
Time Series Forecasting
- Forecasting Sequential Data Using Consistent Koopman Autoencoders, ICML'20. [paper] [official code]
- Adversarial Attacks on Probabilistic Autoregressive Forecasting Models, ICML'20. [paper] [official code]
- Influenza Forecasting Framework based on Gaussian Processes, ICML'20. [paper]
- Deep Factors for Forecasting, ICML'19. [paper]
- Coherent Probabilistic Forecasts for Hierarchical Time Series, ICML'17. [paper]
ICLR 201X-2020
General Time Series Analysis
- Interpolation-Prediction Networks for Irregularly Sampled Time Series, ICLR'19. [paper] [official code]
- SOM-VAE: Interpretable Discrete Representation Learning on Time Series, ICLR'19. [paper] [official code]
Time Series Forecasting
- N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, ICLR'20. [paper] [official code]
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting, ICLR'18. [paper] [official code]
- Automatically Inferring Data Quality for Spatiotemporal Forecasting, ICLR'18. [paper]
KDD 201X-2020
General Time Series Analysis
- Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns, KDD'20. [paper] [code]
- Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data, KDD'20. [paper] [official code]
- Online Amnestic DTW to allow Real-Time Golden Batch Monitoring, KDD'19. [paper]
- Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis, KDD'18. [paper]
- Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data, KDD'17. [paper]
Time Series Forecasting
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks, KDD'20. [paper] [official code]
- Attention based Multi-Modal New Product Sales Time-series Forecasting, KDD'20. [paper]
- Forecasting the Evolution of Hydropower Generation, KDD'20. [paper]
- Modeling Extreme Events in Time Series Prediction, KDD'19. [paper]
- Multi-Horizon Time Series Forecasting with Temporal Attention Learning, KDD'19. [paper]
- Regularized Regression for Hierarchical Forecasting Without Unbiasedness Conditions, KDD'19. [paper]
- Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units, KDD'19. [paper] [official code]
- Dynamic Modeling and Forecasting of Time-evolving Data Streams, KDD'19. [paper] [official code]
- DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events, KDD'19. [paper] [official code]
- Stock Price Prediction via Discovering Multi-Frequency Trading Patterns, KDD'17. [paper] [official code]
Time Series Anomaly Detection
- USAD: UnSupervised Anomaly Detection on Multivariate Time Series, KDD'20. [paper] [official code]
- RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks, KDD'20 MiLeTS. [paper]
- Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network, KDD'19. [paper] [official code]
- Time-Series Anomaly Detection Service at Microsoft, KDD'19. [paper]
- Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding, KDD'18. [paper] [official code]
- Anomaly Detection in Streams with Extreme Value Theory, KDD'17. [paper]
AAAI 201X-2020
General Time Series Analysis
- Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets, AAAI'20. [paper] [official code]
- DATA-GRU: Dual-Attention Time-Aware Gated Recurrent Unit for Irregular Multivariate Time Series, AAAI'20. [paper]
- Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series, AAAI'20. [paper] [official code]
- Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Series, AAAI'20. [paper] [official code]
- Relation Inference among Sensor Time Series in Smart Buildings with Metric Learning, AAAI'20. [paper]
- TapNet: Multivariate Time Series Classification with Attentional Prototype Network, AAAI'20. [paper] [official code]
- RobustSTL: A Robust Seasonal-Trend Decomposition Procedure for Long Time Series, AAAI'19. [paper] [code]
- Estimating the Causal Effect from Partially Observed Time Series, AAAI'19. [paper]
- Adversarial Unsupervised Representation Learning for Activity Time-Series, AAAI'19. [paper]
- Fourier Feature Approximations for Periodic Kernels in Time-Series Modelling, AAAI'18. [paper]
Time Series Forecasting
- Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values, AAAI'20. [paper]
- Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting, AAAI'20. [paper] [official code]
- Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting, AAAI'20. [paper] [official code]
- Self-Attention ConvLSTM for Spatiotemporal Prediction, AAAI'20. [paper]
- Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting, AAAI'20. [paper]
- Spatio-Temporal Graph Structure Learning for Traffic Forecasting, AAAI'20. [paper]
- GMAN: A Graph Multi-Attention Network for Traffic Prediction, AAAI'20. [paper] [official code]
- Cogra: Concept-drift-aware Stochastic Gradient Descent for Time-series Forecasting, AAAI'19. [paper]
- Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting, AAAI'19. [paper]
- Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting, AAAI'19. [paper] [official code]
- MRes-RGNN: A Novel Deep Learning based Framework for Traffic Prediction, AAAI'19. [paper]
- DeepSTN+: Context-aware Spatial Temporal Neural Network for Crowd Flow Prediction in Metropolis, AAAI'19. [paper] [official code]
- Incomplete Label Multi-task Deep Learning for Spatio-temporal Event Subtype Forecasting, AAAI'19. [paper]
- Learning Heterogeneous Spatial-Temporal Representation for Bike-sharing Demand Prediction, AAAI'19. [paper]
- Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting, AAAI'19. [paper]
Time Series Anomaly Detection
- A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data, AAAI'19. [paper]
- Non-parametric Outliers Detection in Multiple Time Series A Case Study: Power Grid Data Analysis, AAAI'18. [paper]
IJCAI 201X-2020
General Time Series Analysis
- RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering, IJCAI'19. [paper]
- E2GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation, IJCAI'19. [paper]
- Causal Inference in Time Series via Supervised Learning, IJCAI'18. [paper]
Time Series Forecasting
- PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction, IJCAI'20. [paper] [official code]
- LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks, IJCAI'20. [paper]
- Cross-Interaction Hierarchical Attention Networks for Urban Anomaly Prediction, IJCAI'20. [paper]
- Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting, IJCAI'19. [paper]
- Explainable Deep Neural Networks for Multivariate Time Series Predictions, IJCAI'19. [paper]
- Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns. [paper]
- Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. [paper] [official code]
- LC-RNN: A Deep Learning Model for Traffic Speed Prediction. [paper]
- GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction, IJCAI'18. [paper] [official code]
- Hierarchical Electricity Time Series Forecasting for Integrating Consumption Patterns Analysis and Aggregation Consistency, IJCAI'18. [paper]
- NeuCast: Seasonal Neural Forecast of Power Grid Time Series, IJCAI'18. [paper] [official code]
- A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction, IJCAI'17. [paper] [code]
- Hybrid Neural Networks for Learning the Trend in Time Series, IJCAI'17. [paper]
Time Series Anomaly Detection
- BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series, IJCAI'19. [paper] [official code]
- Outlier Detection for Time Series with Recurrent Autoencoder Ensembles, IJCAI'19. [paper] [official code]
- Stochastic Online Anomaly Analysis for Streaming Time Series, IJCAI'17. [paper]
Time Series Clustering
- Linear Time Complexity Time Series Clustering with Symbolic Pattern Forest, IJCAI'19. [paper]
- Similarity Preserving Representation Learning for Time Series Clustering, IJCAI'19. [paper]
Time Series Classification
- A new attention mechanism to classify multivariate time series, IJCAI'20. [paper]
SIGMOD VLDB ICDE 201X-2020
General Time Series Analysis
- Debunking Four Long-Standing Misconceptions of Time-Series Distance Measures, SIGMOD'20. [paper] [official code]
- Database Workload Capacity Planning using Time Series Analysis and Machine Learning, SIGMOD'20. [paper]
- Mind the gap: an experimental evaluation of imputation of missing values techniques in time series, VLDB'20. [paper] [official code]
- Active Model Selection for Positive Unlabeled Time Series Classification, ICDE'20. [paper] [official code]
- ExplainIt! -- A declarative root-cause analysis engine for time series data, SIGMOD'19. [paper]
- Cleanits: A Data Cleaning System for Industrial Time Series, VLDB'19. [paper]
- Matrix Profile X: VALMOD - Scalable Discovery of Variable-Length Motifs in Data Series, SIGMOD'18. [paper]
- Effective Temporal Dependence Discovery in Time Series Data, VLDB'18. [paper]
Time Series Anomaly Detection
- Series2Graph: graph-based subsequence anomaly detection for time series, VLDB'20. [paper] [official code]
- Neighbor Profile: Bagging Nearest Neighbors for Unsupervised Time Series Mining, ICDE'20. [paper]
- Automated Anomaly Detection in Large Sequences, ICDE'20. [paper] [official code]
- User-driven error detection for time series with events, ICDE'20. [paper]
Misc 201X-2020
General Time Series Analysis
- STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks, WWW'19. [paper] [official code]
- GP-VAE: Deep probabilistic time series imputation, AISTATS'20. [paper] [official code]
- DYNOTEARS: Structure Learning from Time-Series Data, AISTATS'20. [paper]
- Personalized Imputation on Wearable-Sensory Time Series via Knowledge Transfer, CIKM'20. [paper]
- Order-Preserving Metric Learning for Mining Multivariate Time Series, ICDM'20. [paper]
- Learning Periods from Incomplete Multivariate Time Series, ICDM'20. [paper]
- Foundations of Sequence-to-Sequence Modeling for Time Series, AISTATS'19. [paper]
Time Series Forecasting
- Hierarchically Structured Transformer Networks for Fine-Grained Spatial Event Forecasting, WWW'20. [paper]
- HTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction, WWW'20. [paper] [official code]
- Traffic Flow Prediction via Spatial Temporal Graph Neural Network, WWW'20. [paper]
- Towards Fine-grained Flow Forecasting: A Graph Attention Approach for Bike Sharing Systems, WWW'20. [paper]
- Domain Adaptive Multi-Modality Neural Attention Network for Financial Forecasting, WWW'20. [paper]
- Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting, ICDM'20. [paper]
- Probabilistic Forecasting with Spline Quantile Function RNNs, AISTATS'19. [paper]
- DSANet: Dual self-attention network for multivariate time series forecasting, CIKM'19. [paper]
- RESTFul: Resolution-Aware Forecasting of Behavioral Time Series Data, CIKM'18. [paper]
- Forecasting Wavelet Transformed Time Series with Attentive Neural Networks, ICDM'18. [paper]
- A Flexible Forecasting Framework for Hierarchical Time Series with Seasonal Patterns: A Case Study of Web Traffic, SIGIR'18. [paper]
- Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks, SIGIR'18. [paper] [official code]
Time Series Anomaly Detection
- Multivariate Time-series Anomaly Detection via Graph Attention Network, ICDM'20. [paper] [code]
- MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives, ICDM'20. [paper] [official code]
- Cross-dataset Time Series Anomaly Detection for Cloud Systems, ATC'19. [paper]
- Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications, WWW'18. [paper] [official code]
mook
- Stanford CS229: Machine Learning
- Applied Machine Learning
- Practical Deep Learning for Coders (2020)
- Machine Learning with Graphs (Stanford)
- Probabilistic Machine Learning
- Introduction to Deep Learning (MIT)
- Deep Learning: CS 182
- Deep Unsupervised Learning
- NYU Deep Learning SP21
- CS224N: Natural Language Processing with Deep Learning
- CMU Neural Networks for NLP
- CS224U: Natural Language Understanding
- CMU Advanced NLP
- Multilingual NLP
- Advanced NLP
- Deep Learning for Computer Vision
- Deep Reinforcement Learning
- Full Stack Deep Learning
- AMMI Geometric Deep Learning Course (2021)
Pytorch
Christian Perone  - 발표자료: https://speakerdeck.com/perone/pytorch-under-the-hood
- 블로그: http://blog.christianperone.com/ Build Deep Learning Projects (Complete Video Series for FREE ) ==============================================
-
Making your RL Projects in 20 Minutes : https://www.edyoda.com/course/1421
-
Style Transfer, Face Generation using GANs in 20 minutes : https://www.edyoda.com/course/1418
-
Language and Machine Learning in 20 minutes : https://www.edyoda.com/course/1419
-
AI Project - Web application for Object Identification : https://www.edyoda.com/course/1185
-
Dog Breed Prediction : https://www.edyoda.com/course/1336
DL papers
- ast-SCNN: Fast Semantic Segmentation Network.
- 123 fps on 2048x1024 images (2x faster than current state-of-the-art).
- https://arxiv.org/abs/1902.04502
- Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (https://arxiv.org/pdf/1606.00915.pdf) Source code: https://github.com/vietnguyen91/Deeplab-pytorch
- Correlational Neural Network. CV, TL, RPL.
- Reasoning With Neural Tensor Networks for Knowledge Base Completion. NLP, ML. Blog-post
- Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. NLP, DL, CQA. Code
- Common Representation Learning Using Step-based Correlation Multi-Modal CNN. CV, TL, RPL. Code
- ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs. NLP, AT, DL, STS. Code
- Combining Neural, Statistical and External Features for Fake News Stance Identification. NLP, IR, DL. Code
- WIKIQA: A Challenge Dataset for Open-Domain Question Answering. NLP, DL, CQA. Code
- Siamese Recurrent Architectures for Learning Sentence Similarity. NLP, STS, DL. Code
- Teaching Machines to Read and Comprehend. NLP, AT, DL. Code
- Improved Representation Learning for Question Answer Matching. NLP, AT, DL, CQA. Code
- Map-Reduce for Machine Learning on Multicore]. map-reduce, hadoop, ML.. MR, ML. Code
- Convolutional Neural Tensor Network Architecture for Community Question Answering. NLP, DL, CQA. Code
- External features for community question answering. NLP, DL, CQA. Code
- Language Identification and Disambiguation in Indian Mixed-Script. NLP, IR, ML. Blog-post
- Construction of a Semi-Automated model for FAQ Retrieval via Short Message Service. NLP, IR, ML. Code
Table of Contents
AI Tutorials
Tutorials 2023
- Everything You Need to Know about Transformers: Architectures, Optimization, Applications, and Interpretation, AAAI 2023. [Link]
- On Explainable AI: From Theory to Motivation, Industrial Applications, XAI Coding & Engineering Practices, AAAI 2023. [Link]
Tutorials 2022
- Causality and deep learning: synergies, challenges& opportunities for research, ICML 2022. [Link TBD]
- Bridging Learning and Decision Making, ICML 2022. [Link TBD]
- Facilitating a smoother transition to Renewable Energy with AI (AI4Renewables), ICLR 2022 Social. [Link] [slides]
- Optimization in ML and DL - A discussion on theory and practice, ICLR 2022 Social. [slides]
- Beyond Convolutional Neural Networks, CVPR 2022. [Link]
- Evaluating Models Beyond the Textbook: Out-of-distribution and Without Labels, CVPR 2022. [Link]
- Sparsity Learning in Neural Networks and Robust Statistical Analysis, CVPR 2022. [Link]
- Denoising Diffusion-based Generative Modeling: Foundations and Applications, CVPR 2022. [Link]
- On Explainable AI: From Theory to Motivation, Industrial Applications, XAI Coding & Engineering Practices, AAAI 2022. [Link]
- Deep Learning on Graphs for Natural Language Processing, AAAI 2022. [Link]
- Bayesian Optimization: From Foundations to Advanced Topics, AAAI 2022. [Link]
Tutorials 2021
- The Art of Gaussian Processes: Classic and Contemporary, NeurIPS 2021. [Link] [slides]
- Self-Supervised Learning: Self-Prediction and Contrastive Learning, , NeurIPS 2021. [slides] [vedio]
- Self-Attention for Computer Vision, ICML 2021. [Link]
- Continual Learning with Deep Architectures, ICML 2021. [Link]
- Responsible AI in Industry: Practical Challenges and Lessons Learned, ICML 2021. [Link]
- Self-Supervision for Learning from the Bottom Up, ICLR 2021 Talk. [Link]
- Geometric Deep Learning: the Erlangen Programme of ML, ICLR 2021 Talk. [Link]
- Moving beyond the fairness rhetoric in machine learning, ICLR 2021 Talk. [Link]
- Is My Dataset Biased, ICLR 2021 Talk. [Link]
- Interpretability with skeptical and user-centric mind, ICLR 2021 Talk. [Link]
- AutoML: A Perspective where Industry Meets Academy, KDD 2021. [Link]
- Automated Machine Learning on Graph, KDD 2021. [Link]
- Toward Explainable Deep Anomaly Detection, KDD 2021. [Link]
- Fairness and Explanation in Clustering and Outlier Detection, KDD 2021. [Link]
- Real-time Event Detection for Emergency Response, KDD 2021. [Link]
- Machine Learning Explainability and Robustness: Connected at the Hip, KDD 2021. [Link]
- Machine Learning Robustness, Fairness, and their Convergence, KDD 2021. [Link]
- Counterfactual Explanations in Explainable AI: A Tutorial, KDD 2021. [Link]
- Causal Inference and Machine Learning in Practice with EconML and CausalML: Industrial Use Cases at Microsoft, TripAdvisor, Uber, KDD 2021. [Link]
- Normalization Techniques in Deep Learning: Methods, Analyses, and Applications, CVPR 2021. [Link]
- Normalizing Flows and Invertible Neural Networks in Computer Vision, CVPR 2021. [Link]
- Theory and Application of Energy-Based Generative Models, CVPR 2021. [Link]
- Adversarial Machine Learning in Computer Vision, CVPR 2021. [Link]
- Practical Adversarial Robustness in Deep Learning: Problems and Solutions, CVPR 2021. [Link]
- Leave those nets alone: advances in self-supervised learning, CVPR 2021. [Link]
- Interpretable Machine Learning for Computer Vision, CVPR 2021. [Link]
- Learning Representations via Graph-structured Networks, CVPR 2021. [Link]
- Reviewing the Review Process, ICCV 2021. [Link]
- Meta Learning and Its Applications to Natural Language Processing, ACL 2021. [Link]
- Deep generative modeling of sequential data with dynamical variational autoencoders, ICASSP 2021. [Link]
Tutorials 2020
- Deep Implicit Layers - Neural ODEs, Deep Equilibirum Models, and Beyond, NeurIPS 2020. [Link]
- Practical Uncertainty Estimation and Out-of-Distribution Robustness in Deep Learning, NeurIPS 2020. [Link]
- Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities, NeurIPS 2020. [Link]
- Advances in Approximate Inference, NeurIPS 2020. [Link]
- There and Back Again: A Tale of Slopes and Expectations, NeurIPS 2020. [Link]
- Federated Learning and Analytics: Industry Meets Academia, NeurIPS 2020. [Link]
- Machine Learning with Signal Processing, ICML 2020. [Link]
- Bayesian Deep Learning and a Probabilistic Perspective of Model Construction, ICML 2020. [slides] [video]
- Representation Learning Without Labels, ICML 2020. [slides] [video]
- Recent Advances in High-Dimensional Robust Statistics, ICML 2020. [Link]
- Submodular Optimization: From Discrete to Continuous and Back, ICML 2020. [Link]
- Deep Learning for Anomaly Detection, in KDD 2020. [Link] [video]
- Learning with Small Data, in KDD 2020. [Link]
Tutorials 201X
- Adversarial Machine Learning, ICLR 2019 Keynote. [slides]
- Introduction to GANs, CVPR 2018. [slides]
- Which Anomaly Detector should I use, ICDM 2018. [slides]
AI Surveys
General
- Deep learning, in Nature 2015. [paper]
- Deep learning in neural networks: An overview, in Neural networks 2015. [paper]
Transformer and Attention
- A survey on visual transformer, in IEEE TPAMI 2022. [paper]
- Transformers in vision: A survey, in ACM Computing Surveys 2021. [paper]
- Efficient transformers: A survey, in arXiv 2022. [paper]
- A General Survey on Attention Mechanisms in Deep Learning, in IEEE TKDE 2022. [paper]
- Attention, please! A survey of neural attention models in deep learning, in Artificial Intelligence Review 2022. [paper]
- An attentive survey of attention models, in ACM TIST 2021. [paper]
- Attention in natural language processing, in IEEE TNNLS 2020. [paper]
Self-Supervised Learning
- Self-supervised visual feature learning with deep neural networks: A survey, in IEEE TPAMI 2020. [paper]
- Self-supervised Learning: Generative or Contrastive, TKDE'21. [paper]
- Self-Supervised Representation Learning: Introduction, advances, and challenges, SPM'22. [paper]
Graph Neural Networks
- A comprehensive survey on graph neural networks, TNNLS'20. [paper]
- Deep learning on graphs: A survey, TKDE'20. [paper]
- Graph neural networks: A review of methods and applications, AI Open'20. [paper]
- Self-Supervised Learning of Graph Neural Networks: A Unified Review, TPAMI'22. [paper]
- Graph Self-Supervised Learning: A Survey, TKDE'22. [paper]
- Self-supervised learning on graphs: Contrastive, generative, or predictive, TKDE'21. [paper]
Federated Learning
- Federated machine learning: Concept and applications, TIST'19. [paper]
- Advances and open problems in federated learning, now'21. [paper]
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection, TKDE'21. [paper]
- A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions, CSUR'21. [paper]
- A survey on federated learning, Knowledge-Based Systems'21. [paper]
- A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond, JIOT'20. [paper]
- Federated learning: Challenges, methods, and future directions, SPM'20. [paper]
XAI
- Explaining deep neural networks and beyond: A review of methods and applications, PIEEE'21. [paper]
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Information Fusion'20. [paper]
- A survey on the explainability of supervised machine learning, JAIR'21. [paper]
- Techniques for Interpretable Machine Learning, CACM'19. [paper]
AutoML
- AutoML: A survey of the state-of-the-art, Knowledge-Based Systems'21. [paper]
- Benchmark and survey of automated machine learning frameworks, JAIR'21. [paper]
- AutoML to Date and Beyond: Challenges and Opportunities, CSUR'22. [paper]
- Automated Machine Learning on Graphs: A Survey, IJCAI'21. [paper]
- Others: awesome-automl-papers. [repo]
Deep Generative Models
- NIPS 2016 Tutorial: Generative Adversarial Networks, arXiv'17. [paper]
- Generative adversarial networks: An overview, SPM'18. [paper]
- A review on generative adversarial networks: Algorithms, theory, and applications, TKDE'21. [paper]
- A survey on generative adversarial networks: Variants, applications, and training, CSUR'22. [paper]
- An Introduction to Variational Autoencoders, now'19. [paper]
- Dynamical Variational Autoencoders: A Comprehensive Review, now'21. [paper]
- Advances in variational inference, TPAMI'19. [paper]
- Normalizing flows: An introduction and review of current methods, TPAMI'20. [paper]
- Normalizing Flows for Probabilistic Modeling and Inference, JMLR'21. [paper]
N-Shot Learning
- A survey of zero-shot learning: Settings, methods, and applications, in TIST 2019. [paper]
- Generalizing from a few examples: A survey on few-shot learning, in CSUR 2020. [paper] [Link]
- What Can Knowledge Bring to Machine Learning?—A Survey of Low-shot Learning for Structured Data, in TIST 2022. [paper]
- A Survey of Few-Shot Learning: An Effective Method for Intrusion Detection, in SCN 2022. [paper]
- Few-Shot Learning on Graphs: A Survey, in arXiv 2022. [paper]
- A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities, in arXiv 2022. [paper]
Anomaly Detection and OOD
- A unifying review of deep and shallow anomaly detection, PIEEE'21. [paper]
- Deep learning for anomaly detection: A review, CSUR'20. [paper]
- A Comprehensive Survey on Graph Anomaly Detection with Deep Learning, TKDE'21. [paper]
- Graph based anomaly detection and description: a survey, DMKD'15. [paper]
- Anomaly detection in dynamic networks: a survey, WICS'15. [paper]
- Anomaly detection: A survey, CSUR'09. [paper]
- A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges, arXiv'21. [paper]
- Self-Supervised Anomaly Detection: A Survey and Outlook, arXiv'21. [paper]
Label-noise Learning
- A Survey of Label-noise Representation Learning: Past, Present and Future, arXiv'21. [paper] [link]
- Learning from Noisy Labels with Deep Neural Networks: A Survey, TNNLS'22. [paper] [link]
- Classification in the presence of label noise: a survey, TNNLS'13. [paper]
Imbalanced-data Learning
- Learning from imbalanced data, TKDE'09. [paper]
- A Systematic Review on Imbalanced Data Challenges in Machine Learning: Applications and Solutions, CSUR'20. [paper]
- Imbalance problems in object detection: A review, TPAMI'20. [paper]
Deep Reinforcement Learning
Domain Adaptation
- Generalizing to unseen domains: A survey on domain generalization, TKDE'22. [paper]
- A survey of unsupervised deep domain adaptation, TIST'21. [paper]
- A review of domain adaptation without target labels, TPAMI'19. [paper]
Others
- A continual learning survey: Defying forgetting in classification tasks, in IEEE TPAMI 2021. [paper]
- Learning under concept drift: A review, in IEEE TKDE 2018. [paper]
- Learning in nonstationary environments: A survey, MCI'15. [paper]
- Online learning: A comprehensive survey, Neucom'21. [paper]
- A survey on transfer learning, TKDE'09. [paper]
- A Comprehensive Survey on Transfer Learning, PIEEE'21. [paper]
- A survey on multi-task learning, TKDE'21. [paper]
- Bayesian statistics and modelling, Nature Reviews Methods Primers'21. [paper]
- Meta-learning in neural networks: A survey, arXiv'21. [paper]
- Deep Long-Tailed Learning: A Survey, arXiv'21. [paper] [link]
- Learning to optimize: A primer and a benchmark, arXiv'21. [paper]
data science tutorial
Tracking Bird Migration Using Python 3 Source Code & Tutorial: https://goo.gl/BS4rQc
Data Science Tutorial Read Here: https://goo.gl/ZPyZBX
Deep Learning (CS 1470)
http://cs.brown.edu/courses/cs1470/index.html
Deep Learning Book
https://www.deeplearningbook.org/ [GitHub] https://github.com/janishar/mit-deep-learning-book-pdf [tutorial] http://www.iro.umontreal.ca/~bengioy/talks/lisbon-mlss-19juillet2015.pdf [videos] https://www.youtube.com/channel/UCF9O8Vj-FEbRDA5DcDGz-Pg/videos
Dive into Deep Learning
https://d2l.ai/ [GitHub] https://github.com/d2l-ai/d2l-en [pdf] https://en.d2l.ai/d2l-en.pdf [STAT 157] http://courses.d2l.ai/berkeley-stat-157/index.html
Neural Network Design
http://hagan.okstate.edu/nnd.html [pdf] http://hagan.okstate.edu/NNDesign.pdf
Neural Networks and Deep Learning
http://neuralnetworksanddeeplearning.com/ [GitHub] https://github.com/mnielsen/neural-networks-and-deep-learning [pdf] http://static.latexstudio.net/article/2018/0912/neuralnetworksanddeeplearning.pdf [solutions] https://github.com/reachtarunhere/nndl/blob/master/2016-11-22-ch1-sigmoid-2.md
Theories of Deep Learning (STATS 385)
https://stats385.github.io/ [videos] https://www.researchgate.net/project/Theories-of-Deep-Learning
Theoretical Principles for Deep Learning (IFT 6085)
http://mitliagkas.github.io/ift6085-dl-theory-class-2019/
A collection of links of videos(youtube) by course
https://github.com/kmario23/deep-learning-drizzle/blob/master/README.md
A collection of tutorial Jupyter notebooks
https://github.com/jupyter/jupyter/wiki/A-gallery-of-interesting-Jupyter-Notebooks
the matrix calculus
https://explained.ai/matrix-calculus/index.html
etc
https://fleuret.org/ee559/ http://deep-learning-phd-course-2018-xb.s3-website-ap-southeast-1.amazonaws.com/ https://www.fast.ai/
Annotation detect
- Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
Tensorflow
The TenSorFlow is an Open Soruce Software Library for Machine Intellience. This repository are many jupyter note-pad like TesroFlow turorials, step books, and others.
DeepMind's WaveNet
- Code: source
DeepVoice
Deep Voice: Real-Time Neural Text-to-Speech for Production
- Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, Yongguo Kang, Xian Li, John Miller, Jonathan Raiman, Shubho Sengupta, Mohammad Shoeybi
- [paper]
- [Ref.code
Very simple TensorFlow examples
GAN
Style-based GAN
Pytorch a2c
- Advantage Actor Critic (A2C), a synchronous deterministic version of A3C
- Volodymyr Mnih1
- Adri
a Puigdom
enech Badia1 - Mehdi Mirza1,2
- Alex Graves1
- Tim Harley1
- Timothy P. Lillicrap1
- David Silver1
- Koray Kavukcuoglu1
- code
Sequence to Sequence -- Video to Text
- Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue, Raymond Mooney, Trevor Darrell, Kate Saenko, arxiv, 2015
- [code]
- [paper]
Sequence to Sequence -- chatbot
Show and Tell: A Neural Image Caption Generator
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio, ICLR, 2014
- [code]
- [paper]
Learning Deep Features for Discriminative Localization
Deep Visual Analogy-Making
Deep Convolutional Generative Adversarial Networks
End-To-End Memory Networks
Character-Aware Neural Language Models
Deep Reinforcement Learning
Human-level control through deep reinforcement learning
Deep Reinforcement Learning with Double Q-learning
Using Deep Q-Network to Learn How To Play Flappy Bird
- Kevin Chen, Deep Reinforcement Learning for Flappy Bird, Report from http://cs229.stanford.edu/ 2015 project
- [code]
- [report]
Semi-Supervised Learning with Ladder Network
- A Rasmus, H Valpola, M Honkala, M Berglund, and T Raiko, NIPS, 2015
- [code]
- [paper]
- [Additional Material]
Convolutional Neural Networks for Sentence Classification
- Yoon Kim, EMNLP, 2014
- [code]
- [paper]
- [Additional Material]
Black-Box Adversarial Perturbations
Implementation of Simple Black-Box Adversarial Perturbations for Deep Networks in Keras fork from link
python cifar100.py
to train a basic CNN for cifar100 and save that file.python find_better.py <model>
to go through cifar100 test dataset and find a good image (as defined in the paper).python per.py <KERAS_MODEL> <IMAGE_in_NUMPY>
: currently works for cifar images only.
Deep Residual Learning for Image Recognition
colornet - Neural Network to colorize grayscale images
- pavelgonchar
- [github page]
- [paper1 - Hypercolumns for Object Segmentation and Fine-grained Localization]
- [paper2 - VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION]
- [explanation]
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
A Neural Algorithm of Artistic Style
- Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
- [code - Neural style in TensorFlow!]
- [blog - http://www.anishathalye.com/2015/12/19/an-ai-that-can-mimic-any-artist/]
- [A Neural Algorithm of Artistic Style]
콘크리트 구조물 균열 탐지 및 분석
csv ttols
https://github.com/eBay/tsv-utils.git
Sequence Generative Adversarial Networks
https://github.com/shawLyu/HR-Depth
Reference
- CV | Computer Vision
- TL | Transfer Learning
- RPL | Representation Learning
- CQA | Community Question Answering
- STS | Sentence Text Similarity
- IR | Information Retrieval
- AT | Attention
- MR | Map Reduce
- ASR | Acoustic Scene Recognition
- DL | Deep Learning
- NLP | Natural Language Processing
- ML | Machine Learning.