This repository collects many papers related to negative sampling methods for Recommendation Systems (RS). Existing negative sampling methods can be roughly divided into five categories: Static Negative Sampling, Hard Negative Sampling, Adversarial Sampling, Graph-based Sampling and Additional data enhanced Sampling.
-
Static Negative Sampling
-
UAI(2009) BPR: Bayesian Personalized Ranking from Implicit Feedback.[pdf]
-
RecSys(2012) Real-Time Top-N Recommendation in Social Streams.[pdf]
-
RecSys(2018) Word2vec applied to Recommendation: Hyperparameters Matter.[pdf]
-
WSDM(2021) Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph.[pdf]
-
-
Hard Negative Sampling
-
SIGIR(2013) Optimizing Top-N Collaborative Filtering via Dynamic Negative Item Sampling.[pdf]
-
WSDM(2014) Improving Pairwise Learning for Item Recommendation from Implicit Feedback.[pdf]
-
CIKM(2015) Improving Latent Factor Models via Personalized Feature Projection for One Class Recommendation.[pdf]
-
WAIM(2016) RankMBPR: Rank-aware Mutual Bayesian Personalized Ranking for Item Recommendation.[pdf]
-
AAAI(2018) WalkRanker: A Unified Pairwise Ranking Model with Multiple Relations for Item Recommendation.[pdf]
-
arXiv(2020) Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering.[pdf] | [code]
-
SIGIR(2020) Bundle Recommendation with Graph Convolutional Networks[pdf]
-
KDD(2021) Curriculum Meta-Learning for Next POI Recommendation.[pdf]
-
ICDE(2023) Bayesian Negative Sampling for Recommendation.[pdf] | [code]
-
CIKM(2022) A Biased Sampling Method for Imbalanced Personalized Ranking.[pdf]
-
RecSys(2023) Exploring False Hard Negative Sample in Cross-Domain Recommendation.[pdf] | [code]
-
SIGIR(2023) Neighborhood-based Hard Negative Mining for Sequential Recommendation.[pdf] | [code]
-
-
Adversarial Sampling
-
KDD(2018) Neural Memory Streaming Recommender Networks with Adversarial Training.[pdf]
-
CIKM(2018) CFGAN: A Generic Collaborative Filtering Framework based on Generative Adversarial Networks.[pdf]
-
IJCAI(2019) Deep Adversarial Social Recommendation.[pdf]
-
CIKM(2019) Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction.[pdf]
-
AAAI(2019) Adversarial Binary Collaborative Filtering for Implicit Feedback.[pdf]
-
TNLLS(2020) IPGAN: Generating Informative Item Pairs by Adversarial Sampling.[pdf]
-
KDD(2021) PURE: Positive-Unlabeled Recommendation with Generative Adversarial Network.[pdf]
-
KDD(2021) Adversarial Feature Translation for Multi-domain Recommendation.[pdf] | [code]
-
-
Graph-based Sampling
-
WWW(2014) ACRec: a co-authorship based random walk model for academic collaboration recommendation.[pdf]
-
KDD(2018) Graph Convolutional Neural Networks for Web-Scale Recommender Systems.[pdf]
-
WWW(2019) SamWalker: Social Recommendation with Informative Sampling Strategy.[pdf] | [code]
-
WWW(2020) Reinforced Negative Sampling over Knowledge Graph for Recommendation.[pdf] | [code]
-
KDD(2021) MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems.[pdf] | [code]
-
TKDE(2021) SamWalker++: recommendation with informative sampling strategy.[pdf] | [code]
-
CIKM(2021) DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN.[pdf] | [code]
-
-
Additional data enhanced Sampling
-
CIKM(2014) Leveraging Social Connections to Improve Personalized Ranking for Collaborative Filtering.[pdf]
-
CIKM(2016) Social Recommendation with Strong and Weak Ties.[pdf]
-
RecSys(2016) Bayesian Personalized Ranking with Multi-Channel User Feedback. [pdf] | [code]
-
ICTAI(2017)Joint Geo-Spatial Preference and Pairwise Ranking for Point-of-Interest Recommendation.[pdf]
-
CIKM(2017) A Personalised Ranking Framework with Multiple Sampling Criteria for Venue Recommendation.[pdf]
-
WWW(2018) An Improved Sampling for Bayesian Personalized Ranking by Leveraging View Data.[pdf]
-
IJCAI(2019) Reinforced Negative Sampling for Recommendation with Exposure Data.[pdf] | [code]
-
IJCAI(2019) Geo-ALM: POI Recommendation by Fusing Geographical Information and Adversarial Learning Mechanism.[pdf]
-
WI(2019) Bayesian Deep Learning with Trust and Distrust in Recommendation Systems.[pdf]
-
arXiv(2021) Socially-Aware Self-Supervised Tri-Training for Recommendation.[pdf] | [code]
-
WWW(2021) DGCN: Diversified Recommendation with Graph Convolutional Networks.[pdf] | [code]
-
-
未分类
-
CIKM(2016) Tag-Aware Personalized Recommendation Using a Deep-Semantic Similarity Model with Negative Sampling.[pdf]
-
专家系统(2022) GANRec: A negative sampling model with generative adversarial network for recommendation.[pdf] | [code]
-
WWW(2020) Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations. [pdf]
-
Effective and efficient negative sampling in metric learning based recommendation.[pdf]
-
arXiv(2022) Generating Negative Samples for Sequential Recommendation. [pdf]
-
Dynamic negative sampling for recommendation with feature matching.[pdf]
-
RecSys(2023) gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling.[pdf]
-
WI-IAT(2021) Generalized Negative Sampling for Implicit Feedback in Recommendation.[pdf]
-
CIKM(2023) Batch-Mix Negative Sampling for Learning Recommendation Retrievers. [pdf]
-
CSSE(2022) Hybrid Sampling Light Graph Collaborative Filtering for Social Recommendation.[pdf]
-
Soft BPR Loss for Dynamic Hard Negative Sampling in Recommender Systems.[pdf]
-
Collaborative knowledge-aware recommendation based on neighborhood negative sampling.[pdf]
-
SIGIR(2022) Rule-Guided Knowledge-Graph based Negative Sampling for Outfit Recommendation.[pdf]
-
WWW(2022) A Gain-Tuning Dynamic Negative Sampler for Recommendation.[pdf]
-
A Negative Sampling-Based Service Recommendation Method.[pdf]
-
Reinforced PU-learning with Hybrid Negative Sampling Strategies for Recommendation.[pdf]
-
RecSys(2021) A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models.[pdf]
-
SIAM(2023) UFNRec: Utilizing False Negative Samples for Sequential Recommendation.[pdf] | [code]
-
WWW(2023) On the Theories Behind Hard Negative Sampling for Recommendation.[pdf] |
-
Towards Automated Negative Sampling in Implicit Recommendation.[pdf]
-
Development of an offline OOH advertising recommendation system using negative sampling and deep interest network 2024 [pdf]
-
TCSS(2024) Graph Contrastive Learning With Negative Propagation for Recommendation.[pdf]
-
WAIM(2022) User Multi-behavior Enhanced POI Recommendation with Efficient and Informative Negative Sampling.[pdf]
-
Mutual Fund Recommendation Based on Robust Negative Sampling with Graph-Cut Algorithm [pdf]
-
SIGIR (2023) Exploring the Impact of Negative Sampling on Patent Citation Recommendation.[pdf]
-
Reinforcement Learning-Based Explainable Recommendation over Knowledge Graphs with Negative Sampling.[pdf]
-
Negative can be positive: Signed graph neural networks for recommendation.[pdf]
-
MSN(2019) Addressing the Conflict of Negative Feedback and Sampling for Online Ad Recommendation in Mobile Social Networks.[pdf]
-
KDD(2022) FedAttack: Effective and covert poisoning attack on federated recommendation via hard sampling.[pdf]
-
Gan-based recommendation with positive-unlabeled sampling.[pdf]
-
ISAIEE(2022) Time and Space Aggregation Recommendation Model Based on Synthetic Negative Samples.[pdf]
-
WSDM(2023) Relation Preference Oriented High-order Sampling for Recommendation.[pdf] | [code]
-
ICDM(2022) MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation.[pdf]
-
CSSE(2022) Hybrid Sampling Light Graph Collaborative Filtering for Social Recommendation.[pdf]
-
arXir(2021) Knowledge Graph-Enhanced Sampling for Conversational Recommendation System.[pdf]
-
arXir(2024) Adaptive Hardness Negative Sampling for Collaborative Filtering. [pdf] | [code]
-
RecSys(2023) Augmented Negative Sampling for Collaborative Filtering. [pdf] | [code]
-
WSDM(2023) Disentangled Negative Sampling for Collaborative Filtering. [pdf] | [code]
-
-
Non-Sampling