billlody / Thoughts

AI knowledges

Functions

Recommendation system

• Generative Adversarial User Model for Reinforcement Learning Based Recommendation System - Yuan Qi, Le Song
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks - Jian Tang, Ming Zhang
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction - Xiuqiang He, Huawei China
• Deep Neural Networks for YouTube Recommendations - Google
• Wide & Deep Learning for Recommender Systems - Google
• Attention-Based Transactional Context Embedding for Next-Item Recommendation - Wei Liu
• Practical Lessons from Predicting Clicks on Ads at Facebook - Facebook
• DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks - MSRA
• Ranking, Boosting, and Model Adaptation - Microsoft
• Deep & Cross Network for Ad Click Predictions - Google
• Learning to Rank with Nonsmooth Cost Functions - Microsoft Research
• Learning to Rank: From Pairwise Approach to Listwise Approach - MSRA
• Deep Coevolutionary Network: Embedding User and Item Features for Recommendation - Le Song
• TEM: Tree-enhanced Embedding Model for Explainable Recommendation
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems - Jure Leskovec
• Facing Imbalanced Data Recommendations for the Use of Performance Metrics - Fernando De La Torre
• Reproducing kernel Hilbert spaces in Machine Learning - Arthur Gretton
• From RankNet to LambdaRank to LambdaMART: An Overview - Microsoft Research
• IR evaluation methods for retrieving highly relevant documents - Jaana Kekiiliinen

Quant

• Deep Learning for Stock Prediction Using Numerical and Textual Information
• Belief Propagation Algorithm for Portfolio Optimization Problems
• Technological Links and Predictable Returns - Ran Zhang

Books

• Pattern recognition and machine learning - Christopher M.Bishop
• Computer age statistical inference - Bradley Efron and Trevor Hastie
• The Elements of Statistical Learning
• Machine Learning A Probabilistic Perspective - Kevin P. Murphy
• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence - Gary Marcus
• Algorithms for Convex Optimization - Nisheeth K. Vishnoi
• 邱锡鹏：《神经网络与深度学习》, https://nndl.github.io/
• 《自然语言理解斯坦福版本》
• http://snap.stanford.edu/proj/snap-icwsm/ - Jure Leskovec
• Information propagation in complex networks
• From Knowledge Graph Embedding to Ontology Embedding: Region Based Representations of Relational Structures - Steven Schockaert
• Factor Graphs and the Sum-Product Algorithm - Frank R. Kschischang, Hans-Andrea Loeliger
• FAST-PPR: Personalized PageRank Estimation for Large Graphs(PPT)
• Tutorial: Probabilistic Graphical Models, PGM lecture notes: pseudo-likelihood - David Sontag
• Speech and Language Processing An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition - Daniel Jurafsky
• Reinforcement Learning: An Introduction - Andrew G. Barto
• Convex Optimization - Stephen Boyd
• Convex Optimization: Algorithms and Complexity - Sébastien Bubeck
• Mathematical Principles of Fuzzy Logic - Jiri Mockor

Technical materials

• MLlib: Scalable Machine Learning on Spark - Xiangrui Meng, DATABRICKS
• CUDA C/C++ Basics Supercomputing 2011 Tutorial - Cyril Zeller, NVIDIA Corporation
• Scaling Distributed Machine Learning with the Parameter Server - Google, Baidu
• Lectures: TensorFlow for Deep Learning Research, CS20SI
• Meltdown - Mike Hamburg
• An Architecture for Parallel Topic Models
• Spectre Attacks: Exploiting Speculative Execution - Yuval Yarom
• Trinity: A Distributed Graph Engine on a Memory Cloud

Papers

Traditional Machine Learning

• Theory of Kernel Functions - Blaine Nelson, Universit¨at T¨ubingen
• Introduction to RKHS, and some simple kernel algorithms - Arthur Gretton
• Learning with Augmented Features for Heterogeneous Domain Adaptation - Ivor W. Tsang
• Transformation Invariance in Pattern Recognition - Tangent Distance and Tangent Propagation
• The Relationship Between Precision-Recall and ROC Curves - Mark Goadrich
• The Expectation Maximization Algorithm A short tutorial
• A Tutorial on MM Algorithms - Kenneth Lange
• L2P: An Algorithm for Estimating Heavy-tailed Outcomes - Tina Eliassi-Rad
• Causal inference in statistics: An overview - Judea Pearl
• LightGBM: A Highly Efficient Gradient Boosting Decision Tree - MSRA
• Confidence Intervals for the binomial parameter p
• Confidence Bounds & Intervals for Parameters Relating to the Binomial, Negative Binomial, Poisson and Hypergeometric Distributions
• Regression shrinkage and selection via the lasso: a retrospective - Robert Tibshirani
• Algorithms for Non-negative Matrix Factorization - H. Sebastian Seung
• Greedy Function Approximation: A Gradient Boosting Machine - Jerome H. Friedman
• Chapter 1: GENERATIVE AND DISCRIMINATIVE CLASSIFIERS: NAIVE BAYES AND LOGISTIC REGRESSION
• The Bayesian Lasso - George Casella
• PPT: The Bayesian Lasso - Rebecca C. Steorts
• AdaBoost
• Accurate Intelligible Models with Pairwise Interactions - Giles Hooker
• COS 511: Theoretical Machine Learning
• XGBoost: A Scalable Tree Boosting System - Tianqi Chen
• SMOTE: Synthetic Minority Over-sampling Technique - W. Philip Kegelmeyer
• Introduction to RKHS - Gatsby Unit, CSML, UCL
• The Expectation Maximization Algorithm A short tutorial - Sean Borman
• On-line outlier detection and data cleaning - Wei Jiang
• Outlier-Tolerant Kalman Filter of State Vectors in Linear Stochastic System - SUN Guoji
• Forecasting at Scale - Benjamin Letham
• Building ARIMA and ARIMAX Models for Predicting Long-Term Disability Benefit Application Rates in the Public/Private Sectors - Bruce H. Andrews
• A geometric view on Pearson’s correlation coefficient and a generalization of it to non-linear dependencies - Priyantha Wijayatunga
• Simultaneous feature selection and classification using kernel-penalized support vector machines - Jayanta Basak

Interpretation

• Explainable Neural Networks based on Additive Index Models - Vijayan N. Nair
• Consistent Individualized Feature Attribution for Tree Ensembles - Su-In Lee
• A Unified Approach to Interpreting Model Predictions - Su-In Lee
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability - Colin Rowat
• Explainable Machine Learning for Scientific Insights and Discoveries - Jochen Garcke
• Learning to Explain: An Information-Theoretic Perspective on Model Interpretation - Le Song
• Shapley Explainability on the Data Manifold - Faculty
• The Many Shapley Values for Model Explanation - Google
• True to the Model or True to the Data? - Microsoft Research
• An Efficient Explanation of Individual Classifications using Game Theory - Igor Kononenko
• Understanding Conditional Expectation via Vector Projection(PPT) - Cheng-Shang Chang
• Explainable AI for Trees: From Local Explanations to Global Understanding - Su-In Lee

Gaussian Process

• Deep Gaussian Processes(PPT) - Maurizio Filippone
• Dirichlet Processes: A gentle tutorial
• Recurrent Marked Temporal Point Processes: Embedding Event History to Vector - Le Song
• SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity - Jure Leskovec
• Linking Micro Event History to Macro Prediction in Point Process Models - Le Song
• Multivariate Bernoulli distribution - Tower Research
• Rates of Convergence for Sparse Variational Gaussian Process Regression - Mark van der Wilk
• Gaussian Process Inference for Estimating Pharmacokinetic Parameters of Dynamic Contrast-Enhanced MR Images - Ronald M. Summers

Books

• A Practical Guide to Gaussian Processes - Mark van der Wilk
• A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions - Andreas Krause
• BAYESIAN FILTERING AND SMOOTHING - Simo S¨arkk¨a
• Gaussian Processes for Machine Learning - Thomas Dietterich
• Gaussian Processes(tutorial) - Daniel McDuff, MIT Media Lab
• Stochastic Differential Equation Methods for Spatio-Temporal Gaussian Process Regression - Arno Solin

Deep GPs

• Thesis: Deep Gaussian Processes and Variational Propagation of Uncertainty
• Deep Gaussian Processes for Regression using Approximate Expectation Propagation - Richard E. Turner
• Doubly Stochastic Variational Inference for Deep Gaussian Processes - Marc Peter Deisenroth
• How Deep Are Deep Gaussian Processes? - A.L. Teckentrup
• Neural Processes - Yee Whye Teh

Latent Variable GPs

• A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation - Richard E. Turner
• Bayesian Gaussian Process Latent Variable Model - Neil D. Lawrence
• Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models - Neil Lawrence

State Space GPs

• Identification of Gaussian Process State Space Models - James Hensman
• Infinite-Horizon Gaussian Processes - Richard E. Turner
• State-Space Inference and Learning with Gaussian Processes - Carl Edward Rasmussen

Reinforcement Learning

• Bayesian Optimization in AlphaGo - DeepMind
• The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach - Yoshua Bengio
• Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation - Yiannis Demiris
• RL2 : FAST REINFORCEMENT LEARNING VIA SLOW REINFORCEMENT LEARNING - OpenAI
• Reinforced Co-Training - William Yang Wang
• Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning - William Yang Wang
• Behaviour Suite for Reinforcement Learning - DeepMind
• A Tutorial on Thompson Sampling - Zheng Wen
• Gradient Surgery for Multi-Task Learning - Chelsea Finn
• Ensemble Sampling - Benjamin Van Roy
• Suphx: Mastering Mahjong with Deep Reinforcement Learning - MSRA
• What is an RKHS? - Arthur Gretton
• Deep Exploration via Randomized Value Functions - Zheng Wen
• IMPLEMENTATION MATTERS IN DEEP POLICY GRADIENTS: A CASE STUDY ON PPO AND TRPO
• Playing Atari with Deep Reinforcement Learning - DeepMind
• Trust Region Policy Optimization - Michael Jordan
• Efficient Bayesian Clustering for Reinforcement Learning - Zoran Popovie
• Hierarchical clustering with deep Q-learning
• Semi-Unsupervised Clustering Using Reinforcement Learning - Manfred Huber
• Apprenticeship Learning via Inverse Reinforcement Learning - Andrew Y. Ng
• K-Means Clustering based Reinforcement Learning Algorithm for Automatic Control in Robots - Yan Zhai
• Curiosity-driven Exploration by Self-supervised Prediction - Trevor Darrell
• Decision Aid Methodologies In Transportation - Chen Jiang Hang
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning - OpenAI
• Learning Tetris Using the Noisy Cross-Entropy Method
• Vector-based Navigation using Grid-like Representations in Artificial Agents - DeepMind
• Composable Deep Reinforcement Learning for Robotic Manipulation - OpenAI
• Sample Efficient Actor-Critic with Experience Replay - DeepMind
• Hindsight Experience Replay - OpenAI
• Generative Adversarial Imitation Learning - Stefano Ermon
• Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation - Jimmy Ba
• Data-Efficient Reinforcement Learning in Continuous-State POMDPs - Carl Rasmussen
• End-to-End Training of Deep Visuomotor Policies - Pieter Abbeel
• Learning to Act by Predicting the Future - Intel Labs
• A Natural Policy Gradient - Sham Kakade
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning - Ronald J. Williams
• Asynchronous Methods for Deep Reinforcement Learning
• Memory-based control with recurrent neural networks - DeepMind
• Continuous Control with Deep Reinforcement Learning - DeepMind
• Proximal Policy Optimization Algorithms - OpenAI
• Policy Gradient Methods for Reinforcement Learning with Function Approximation - AT&T Labs
• Mastering the Game of Go without Human Knowledge - DeepMind
• End-to-End Training of Deep Visuomotor Policies - Pieter Abbeel
• StarCraft II: A New Challenge for Reinforcement Learning - DeepMind
• Structure Learning in Motor Control: A Deep Reinforcement Learning Model - DeepMind
• Programmable Agents - DeepMind
• Reinforcement Learning with Unsupervised Auxiliary Tasks - DeepMind
• Neural Episodic Control - Google
• Mastering the game of Go with deep neural networks and tree search - DeepMind
• NERVENET: LEARNING STRUCTURED POLICY WITH GRAPH NEURAL NETWORKS
• MuJoCo: A physics engine for model-based control - University of Washington
• Conjugate Gradient Method - Prof.S.Boyd tutorial
• Learning values across many orders of magnitude - DeepMind
• Layer Normalization - Google
• A Log-Linear Model for Unsupervised Text Normalization - Jacob Eisenstein
• A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem - Jinjun Liang

Online Learning

• A Reinforcement Learning Approach to Online Clustering - Aristidis Likas

Transfer Learning

• A Unified Framework for Metric Transfer Learning - Hengjie Song
• Transfer Learning via Learning to Transfer - Qiang Yang
• Learning to Model the Tail - Martial Hebert
• Transfer Learning via Dimensionality Reduction - Qiang Yang
• Domain-Adversarial Training of Neural Networks - Victor Lempitsky
• A Survey on Deep Transfer Learning - Chunfang Liu
• Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer - Terran Lane
• Boosting for Regression Transfer - Peter Stone
• To Transfer or Not To Transfer - Leslie Pack Kaelbling
• Label Efficient Learning of Transferable Representations across Domains and Tasks - Li Fei-Fei
• Multi-Label Classification: An Overview - Ioannis Katakis
• Manifold Alignment using Procrustes Analysis - Sridhar Mahadevan
• Kernel-Based Inductive Transfer - Stefan Kramer
• A Survey on Transfer Learning - Qiang Yang
• Transfer Learning - Jude Shavlik
• Relational Macros for Transfer in Reinforcement Learning - Richard Maclin
• Boosting for Transfer Learning - Qiang Yang
• Transferring Naive Bayes Classifiers for Text Classification - Qiang Yang
• An Experts Algorithm for Transfer Learning - Satinder Singh

Federated Learning

• Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints
• Interpret Federated Learning with Shapley Values - Guan Wang
• Federated Multi-Task Learning - Ameet Talwalkar
• Towards Federated Learning at Scale: System Design - Google

MultiTask

• An Overview of Multi-Task Learning in Deep Neural Networks - Sebastian Ruder
• Multi-Task Learning for HIV Therapy Screening - Max Planck Institute
• Identifying beneficial task relations for multi-task learning in deep neural networks - Anders Søgaard
• An Overview of Multi-Task Learning in Deep Neural Networks - Sebastian Ruder
• A Survey on Multi-Task Learning - Qiang Yang

AutoML

• Sequential Model-Based Optimization for General Algorithm Configuration(extended version) - Kevin Leyton-Brown
• An Evaluation of Sequential Model-Based Optimization for Expensive Blackbox Functions - Kevin Leyton-Brown
• Algorithms for Hyper-Parameter Optimization - Yoshua Bengio, Bal´azs K´egl
• Bayesian optimization explains human active search - Laurent Itti
• AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications - Wenyuan Dai, Qiang Yang
• AutoAugment: Learning Augmentation Policies from Data
• Taking the Human out of Learning Applications: A Survey on Automated Machine Learning - Qiang Yang, Yang Yu
• Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms - Kevin Leyton-Brown
• Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA - Kevin Leyton-Brown
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning - Nando de Freitas
• Taking the Human Out of the Loop: A Review of Bayesian Optimization - Nando de Freitas
• Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures - D. D. Cox
• DARTS: DIFFERENTIABLE ARCHITECTURE SEARCH - CMU and Deepmind
• Deep Boosting - Google Search
• Building an automatic statistician(PPT) - Joshua Tenenbaum, Zoubin Ghahramani
• Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science - Jason H. Moore
• Progressive Neural Architecture Search(PPT)
• NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING - Google Brain
• AdaNet: Adaptive Structural Learning of Artificial Neural Networks - Scott Yang
• Neural Optimizer Search with Reinforcement Learning - Google Brain
• Advanced Model Learning - Chelsea Finn(Tutorial)
• https://simons.berkeley.edu/workshops/abstracts/14378#talk-16132

Meta Learning

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks - Sergey Levine
• Few-Shot Adversarial Learning of Realistic Neural Talking Head Models - Samsung AI Center, Moscow
• Optimization as a Model For Few-Shot Learning - Twitter
• Zero-Shot Learning with Semantic Output Codes - Tom M. Mitchell
• A Model of Inductive Bias Learning - Jonathan Baxter
• Learning to Learn: Model Regression Networks for Easy Small Sample Learning
• TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning - Jaekyun Moon
• META LEARNING SHARED HIERARCHIES - OpenAI

CV

• EDVR: Video Restoration with Enhanced Deformable Convolutional Networks - Ke Yu, Chao Dong, Chen Change Loy, CUHK, NTU, SenseTime
• Deep Flow-Guided Video Inpainting - Bolei Zhou, Chen Change Loy, SenseTime
• Thesis: IMPROVING DIGITAL IMAGE RETRIEVAL TOWARDS IMAGE UNDERSTANDING AND ORGANIZATION - Chen Qi
• Wasserstein GAN - FAIR
• A Theory of Fermat Paths for Non-Line-of-Sight Shape Reconstruction - Srinivasa G. Narasimhan, Ioannis Gkioulekas
• FaceNet: A Unified Embedding for Face Recognition and Clustering - Google
• Deep Residual Learning for Image Recognition - Kaiming He
• Thesis: A guide to convolution arithmetic for deep learning
• Momentum Contrast for Unsupervised Visual Representation Learning - FAIR
• Focal Loss for Dense Object Detection - FAIR
• Training Region-based Object Detectors with Online Hard Example Mining - FAIR
• Prime Sample Attention in Object Detection - Chen Change Loy, Dahua Lin
• Extractive Summarization as Text Matching - Xuanjing Huang
• Learning to Extract Coherent Summary via Deep Reinforcement Learning - Baotian Hu
• Text Summarization Techniques: A Brief Survey - Krys Kochut

NLP

• Sequence to Sequence Learning with Neural Networks - Google
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding - Google AI Language
• Practical Variational Inference for Neural Networks - Alex Graves
• A Fast and Accurate Dependency Parser using Neural Networks - Christopher D. Manning
• Generating Sequences With Recurrent Neural Networks - Alex Graves
• A Critical Review of Recurrent Neural Networks for Sequence Learning - Charles Elkan
• Latent Dirichlet Allocation(LDA) - Michael I. Jordan
• An Introduction to Variational Methods for Graphical Models - Michael I. Jordan
• High Performance NLP: bit.ly/2SmhKY7
• To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks - Noah A. Smith
• Dynamic Topic Models - John D. Lafferty
• Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation - Iryna Gurevych
• A Theoretical andPractical Implementation Tutorial on Topic Modeling and Gibbs Sampling - William M. Darling
• Sequential latent Dirichlet allocation - Changyou Chen
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks - Iryna Gurevych
• Attention Is All You Need - Google Brain
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding - Kristina Toutanova
• Leveraging BERT for Extractive Text Summarization on Lectures - Derek Miller
• ROUGE: A Package for Automatic Evaluation of Summaries - Chin-Yew Lin
• PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization - Peter J. Liu
• Multi-Document Summarization using Sentence-based Topic Models - Yihong Gong
• Generic Text Summarization Using Relevance Measure and Latent Semantic Analysis - Xin Liu
• Fine-tune BERT for Extractive Summarization - Yang Liu
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation - Emiel Krahmer
• ERNIE: Enhanced Representation through Knowledge Integration - Baidu
• Evaluation: Statistical Machine Translation - Chapter 8
• A Neural Probabilistic Language Model - Yoshua Bengio
• A Tutorial on Bayesian Nonparametric Models - David M. Blei
• Introduction to the Dirichlet Process - Billy Fang
• Basics of Dirichlet processes - CS547Q Statistical Modeling with Stochastic Processes
• Dirichlet Processes: Tutorial and Practical Course - UCL
• NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE - Yoshua Bengio
• Effective Approaches to Attention-based Neural Machine Translation - Christopher D. Manning
• Distributed Representations of Sentences and Documents - Google
• Combining NLP Approaches for Rule Extraction from Legal Documents - Guido Governatori
• EDISON: Feature Extraction for NLP, Simplified - Dan Roth
• Understanding the Logical and Semantic Structure of Large Documents - Tim Finin
• On Rule Extraction from Regulations - Wim PETERS
• Chinese Zero Pronoun Resolution with Deep Memory Network - Harbin Institute of Technology
• NON-AUTOREGRESSIVE NEURAL MACHINE TRANSLATION - Salesforce Research

Knowledge Graph

• Variational Knowledge Graph Reasoning - William Yang Wang
• Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures - Andrew McCallum
• Understanding Belief Propagation and its Generalizations - Yair Weiss
• Concept-Oriented Deep Learning - Daniel T. Chang
• Chapter: An Introduction to Conditional Random Fields for Relational Learning
• Scalable Probabilistic Databases with Factor Graphs and MCMC - Gerome Miklau
• Rethinking Knowledge Graph Propagation for Zero-Shot Learning - Eric P. Xing
• Learning Graphs from Data: A Signal Representation Perspective - Pascal Frossard
• Knowledge Base Completion via Coupled Path Ranking - Chin-Yew Lin
• Information Propagation in Interaction Networks - Toon Calders
• Mining Knowledge Graphs from Text - Sameer Singh
• Survey of Markov Logic Networks - Dengdi Liu
• 路径张量分解的知识图谱推理算法
• DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning - William Yang Wang
• Deep Reinforcement Learning for NLP - William Yang Wang
• Learning Deep Structured Semantic Models for Web Search using Clickthrough Data - Microsoft Research
• Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs - Le Song

Graph Model

• An exact mapping between the Variational Renormalization Group and Deep Learning - David J. Schwab
• Boltzmann Machines - Geoffrey E. Hinton
• Bayesian Learning for Neural Networks
• Heat Kernel Based Community Detection - David F. Gleich
• Deep Graph Attention Model - Xiangnan Kong
• Relational inductive biases, deep learning, and graph networks - DeepMind & Google Brain
• Semi-supervised Classification with Graph Convolutional Networks - Max Welling
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering - Pierre Vandergheynst
• Graph Attention Networks - Yoshua Bengio
• The Emerging Field of Signal Processing on Graphs - Pierre Vandergheynst
• Neural Message Passing for Quantum Chemistry - George E. Dahl
• node2vec: Scalable Feature Learning for Networks - Jure Leskovec
• Overlapping Community Detection Using Seed Set Expansion - Inderjit S. Dhillon
• SNARE: A Link Analytic System for Graph Labeling and Risk Detection - Christos Faloutsos
• Constructing Free Energy Approximations and Generalized Belief Propagation Algorithms - Yair Weiss

Geometry Embeddings

• Neural Embeddings of Graphs in Hyperbolic Space - ICL
• Hierarchical Representations with Poincaré Variational Auto-Encoders - DeepMind
• Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry - FAIR
• Low Distortion Delaunay Embedding of Trees in Hyperbolic Plane - Rik Sarkar
• Poincaré Embeddings for Learning Hierarchical Representations - FAIR
• Discriminative Embeddings of Latent Variable Models for Structured Data - Le Song
• DynGEM: Deep Embedding Method for Dynamic Graphs - Yan Liu
• Hyperbolic Entailment Cones for Learning Hierarchical Embeddings - Thomas Hofmann
• Graphlets versus node2vec and struc2vec in the task of network alignment - Tijana Milenkovie
• Tree Edit Distance Learning via Adaptive Symbol Embeddings - Barbara Hammer
• struc2vec: Learning Node Representations from Structural Identity - Daniel R. Figueiredo

Insurance

• Towards a Smart Smoking Cessation App: A 1D-CNN Model Predicting Smoking Events - Yael Benn
• Tweedie Gradient Boosting for Extremely Unbalanced Zero-inflated Data - Yi Yang
• Transforming Underwriting in the Life Insurance Industry - Sears Merritt, MassMutual
• DeepTriangle: A Deep Learning Approach to Loss Reserving - Kevin Kuo
• Neural Network Embedding of the Over-Dispersed Poisson Reserving Model - Mario V. Wuthrich
• Autoencoder Regularized Network For Driving Style Representation Learning - Baidu & IBM
• Bornhuetter-Ferguson as a General Principle of Loss Reserving - Klaus D. Schmidt
• The Chain Ladder Technique — A Stochastic Model - B Zehnwirth
• Flexible Tweedie regression models for continuous data - Celestin C. Kokonendji
• On Gamma Regression Residuals - Hector Zarate
• Chapter 325: Poisson Regression, NCSS.com
• 大数据技术与保险精算：用机器学习提升传统精算模型, 孟生旺
• Reinforcement learning for pricing strategy optimization in the insurance industry - Fernando Fernández
• EARLY WARNING SYSTEM FOR THE EUROPEAN INSURANCE SECTOR - Petr Jakubik
• Experience Studies on Determining Life Premium Insurance Ratings: Practical Approaches - Narcis Eduard MITU

Deep Learning

• Suffcient Representations for Categorical Variables - Stefan Wager
• Particle Flow Bayes’ Rule - Le Song
• Neural Ordinary Differential Equations - David Duvenaud
• Targeted Dropout - Google Brain
• Hybrid computing using a neural network with dynamic external memory - Demis Hassabis
• Neural Turing Machines - Google
• Do CIFAR-10 Classifiers Generalize to CIFAR-10? - Vaishaal Shankar
• Greedy Layer-Wise Training of Deep Networks - Hugo Larochelle
• REGULARIZING NEURAL NETWORKS BY PENALIZING CONFIDENT OUTPUT DISTRIBUTIONS - Geoffrey Hinton
• A Simple Weight Decay Can Improve Generalization - John A. Hertz
• Recurrent Neural Network Regularization - Google Brain
• Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations - Yizhou Sun
• Auto-Encoding Variational Bayes(PPT, paper) - Max Welling
• Variational Lossy Autoencoder - OpenAI
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift - Google

Spurious Relationship

• Domain-Adversarial Training of Neural Networks - Victor Lempitsky
• Invariant Risk Minimization - David Lopez-Paz
• Optimized Data Pre-Processing for Discrimination Prevention - IBM Watson Research Center

Understanding

• Opening the black box of Deep Neural Networks via Information - Naftali Tishby
• Understanding Black-box Predictions via Influence Functions - Percy Liang
• TOWARDS BETTER UNDERSTANDING OF GRADIENT-BASED ATTRIBUTION METHODS FOR DEEP NEURAL NETWORKS - Markus Gross
• Why does deep and cheap learning work so well? - David Rolnick
• INFOBOT: TRANSFER AND EXPLORATION VIA THE INFORMATION BOTTLENECK
• SCALABLE MUTUAL INFORMATION ESTIMATION USING DEPENDENCE GRAPHS - Ann Arbor
• Deep Learning and the Information Bottleneck Principle - Noga Zaslavsky
• Highway Networks - J¨urgen Schmidhuber

Knowledge distilling

• Distilling the Knowledge in a Neural Network - Jeff Dean, Google
• Distilling a Neural Network Into a Soft Decision Tree - Geoffrey Hinton, Google

Label Noise

• Confident Learning: Estimating Uncertainty in Dataset Labels - MIT & Google
• Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks - Arash Vahdat
• L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise - PKU
• Deep Learning is Robust to Massive Label Noise - Nir Shavit
• Combating Label Noise in Deep Learning Using Abstention - Jamaludin Mohd-Yusof
• Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise - Ata Kab´an

Differential Geometry

• Hyperbolic Neural Networks - Thomas Hofmann
• Geometric deep learning: going beyond Euclidean data - Pierre Vandergheynst

Optimization

• Robust Stochastic Approximation Approach to Stochastic Programming - A. SHAPIRO
• Numerical solution of saddle point problems
• Introduction to Saddle Point Problems - Michele Benzi
• Saddle point problems - Olli Mali, Lecture 8
• On the saddle point problem for non-convex optimization - Yoshua Bengio
• Learning from Conditional Distributions via Dual Embeddings - Le Song
• Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices - Zengfeng Huang
• Optimal Algorithms for Non-Smooth Distributed Optimization in Networks - Microsoft
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples - David Wagner
• Generative Adversarial Nets - Yoshua Bengio
• Rates of Convergence for Sparse Variational Gaussian Process Regression - Mark van der Wilk
• An Entropy Search Portfolio for Bayesian Optimization - Nando de Freitas
• Variational Inference: A Review for Statisticians - David M. Blei
• Variational free energy and the Laplace approximation - Will Penny

Metric learning

• Exact Matrix Completion via Convex Optimization - Benjamin Recht
• Stochastic gradient descent on Riemannian manifolds
• The Relationship Between Precision-Recall and ROC Curves - Mark Goadrich
• Thesis: On Structured Matrix Optimization With Two Applications In Statistics - Ting Yuan

Semi-supervised

• Semi-Supervised AUC Optimization without Guessing Labels of Unlabeled Data - Ming Li
• Attention-based Graph Neural Network for Semi-supervised Learning - Google
• SEMI-SUPERVISED KNOWLEDGE TRANSFER FOR DEEP LEARNING FROM PRIVATE TRAINING DATA - Google Brain

Unsupervised

• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations - Olivier Bachem
• Bayesian Hierarchical Clustering - Zoubin Ghahramani

Fairness

• Delayed Impact of Fair Machine Learning - Moritz Hardt

Survival Analysis

• Machine Learning for Survival Analysis(PPT) - Chandan K. Reddy(VirginiaTech)
• A Review on Accelerated Failure Time Models - Manash Pratim Barman
• The Brier Score under Administrative Censoring: Problems and Solutions - Havard Kvamme
• Active Learning based Survival Regression for Censored Data
• Continuous and Discrete-Time Survival Prediction with Neural Networks - Havard Kvamme
• DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks - Mihaela van der Schaar
• Deep Recurrent Survival Analysis - Yong Yu
• DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network - Yuval Kluger
• A Scalable Discrete-Time Survival Model for Neural Networks - Balasubramanian Narasimhan
• Optimal Survival Trees - Agni Orfanoudaki
• Deep Survival Analysis - David Blei
• A General Machine Learning Framework for Survival Analysis - Bernd Bischl
• Random Survival Forests - Michael S. Lauer
• Regularized Parametric Regression for High-dimensional Survival Analysis - Chandan K. Reddy
• Machine Learning for Survival Analysis(PPT) - Yan Li
• A review of survival trees - Hatem Ben-Ameur
• Time-to-Event Prediction with Neural Networks and Cox Regression - Havard Kvamme

Others

• Supervising strong learners by amplifying weak experts - OpenAI
• Kullback-Leibler distance as a measure of the information filtered from multivariate data - Rosario N. Mantegna
• The Kullback–Leibler Divergence as an Estimator of the Statistical Properties of CMB Maps - Andrew D. Jackson
• Maximal Information Coefficient: An Introduction to Information Theory
• Traffic Flow Forecasting Method based on Gradient Boosting Decision Tree - CHEN Jungang
• Using Information Entropy to Measure Bond Risk: An Empirical Investigation - Mei Yu
• Blind Source Separation: Fundamentals and Recent Advances - Eleftherios Kofidis
• Autoregressive with Exogenous Variables and Neural Network Short-Term Load Forecast Models for Residential Low Voltage Distribution Networks - Junwei Lu
• Multi-View Learning in the Presence of View Disagreement - Trevor Darrell