{"id":13751508,"url":"https://github.com/RUCAIBox/Negative-Sampling-Paper","last_synced_at":"2025-05-09T18:31:32.057Z","repository":{"id":39626567,"uuid":"442701003","full_name":"RUCAIBox/Negative-Sampling-Paper","owner":"RUCAIBox","description":"This repository collects 100 papers related to negative sampling methods.","archived":false,"fork":false,"pushed_at":"2023-06-25T07:35:02.000Z","size":28,"stargazers_count":188,"open_issues_count":0,"forks_count":19,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-11-16T04:31:39.880Z","etag":null,"topics":["computer-vision","contrastive-learning","negative-sampling","paper","papers","recommender-system"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RUCAIBox.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-12-29T07:55:41.000Z","updated_at":"2024-11-15T09:13:21.000Z","dependencies_parsed_at":"2024-08-03T09:02:19.056Z","dependency_job_id":null,"html_url":"https://github.com/RUCAIBox/Negative-Sampling-Paper","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RUCAIBox%2FNegative-Sampling-Paper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RUCAIBox%2FNegative-Sampling-Paper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RUCAIBox%2FNegative-Sampling-Paper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RUCAIBox%2FNegative-Sampling-Paper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RUCAIBox","download_url":"https://codeload.github.com/RUCAIBox/Negative-Sampling-Paper/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253303024,"owners_count":21886873,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","contrastive-learning","negative-sampling","paper","papers","recommender-system"],"created_at":"2024-08-03T09:00:47.071Z","updated_at":"2025-05-09T18:31:31.737Z","avatar_url":"https://github.com/RUCAIBox.png","language":null,"funding_links":[],"categories":["特征工程"],"sub_categories":[],"readme":"Negative-Sampling-Paper\n================\n\nThis repository collects 100 papers related to negative sampling methods, covering multiple research fields such as \nRecommendation Systems (**RS**), Computer Vision (**CV**)，Natural Language Processing (**NLP**) and Contrastive Learning (**CL**).\n\nExisting 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**.\n\n- [Category](#Category)\n  - [Static Negative Sampling](#static-negative-sampling)\n  - [Hard Negative Sampling](#hard-negative-sampling)\n  - [Adversarial Sampling](#adversarial-sampling)\n  - [Graph-based Sampling](#graph-based-sampling)\n  - [Additional data enhanced Sampling](#additional-data-enhanced-sampling)\n\n- [Future Outlook](#Future-Outlook)\n  - [False Negative Problem](#false-negative-problem)\n  - [Curriculum Learning](#curriculum-learning)\n  - [Negative Sampling Ratio](#negative-sampling-ratio)\n  - [Debiased Sampling](#debiased-sampling)\n  - [Non-Sampling](#non-sampling)\n\nCategory\n----\n### Static Negative Sampling\n\n-\tBPR: Bayesian Personalized Ranking from Implicit Feedback. `UAI(2009)` **[RS]** **[[PDF](https://arxiv.org/pdf/1205.2618.pdf)]**\n\n-\tReal-Time Top-N Recommendation in Social Streams. `RecSys(2012)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2365952.2365968)]**\n\n-\tDistributed Representations of Words and Phrases and their Compositionality. `NIPS(2013)` **[NLP]** **[[PDF](http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-com.pdf)]**\n\n-\tword2vec Explained: Deriving Mikolov et al.'s Negative-Sampling Word-Embedding Method. `arXiv(2014)` **[NLP]** **[[PDF](http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-com.pdf)]**\n\n-\tDeepwalk: Online learning of social representations. `KDD(2014)` **[GRL]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2623330.2623732)]**\n\n-\tLINE: Large-scale Information Network Embedding. `WWW(2015)` **[GRL]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2736277.2741093)]**\n\n-\tContext- and Content-aware Embeddings for Query Rewriting in Sponsored Search. `SIGIR(2015)` **[NLP]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2766462.2767709)]**\n\n-\tnode2vec: Scalable Feature Learning for Networks. `KDD(2016)` **[NLP]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2939672.2939754)]**\n\n-\tFast Matrix Factorization for Online Recommendation with Implicit Feedback. `SIGIR(2016)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2911451.2911489)]**\n\n-\tWord2vec applied to Recommendation: Hyperparameters Matter. `RecSys(2018)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3240323.3240377)]**\n\n-\tGeneral Knowledge Embedded Image Representation Learning. `TMM(2018)` **[CV]** **[[PDF](http://119.28.72.117/papers/TMM-KnowRep.pdf)]**\n\n-\tAlleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph. `WSDM(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3437963.3441773)]**\n\n\n### Hard Negative Sampling\n\n-\tExample-based learning for view-based human face detection. `TPAMI(1998)` **[CV]** **[[PDF](https://apps.dtic.mil/sti/pdfs/ADA295738.pdf)]**\n\n-\tAdaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model. `T-NN(2008)` **[NLP]** **[[PDF](https://infoscience.epfl.ch/record/82914/files/rr-03-35.pdf)]**\n\n-\tOptimizing Top-N Collaborative Filtering via Dynamic Negative Item Sampling. `SIGIR(2013)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2484028.2484126)]**\n\n-\tBootstrapping Visual Categorization With Relevant Negatives. `TMM(2013)` **[CV]** **[[PDF](https://core.ac.uk/download/pdf/190707126.pdf)]**\n\n-\tImproving Pairwise Learning for Item Recommendation from Implicit Feedback. `WSDM(2014)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2556195.2556248)]**\n\n-\tImproving Latent Factor Models via Personalized Feature Projection for One Class Recommendation. `CIKM(2015)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2806416.2806511)]**\n\n-\tNoise-Contrastive Estimation for Answer Selection with Deep Neural Networks. `CIKM(2016)` **[NLP]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2983323.2983872)]**\n\n-\tRankMBPR: Rank-aware Mutual Bayesian Personalized Ranking for Item Recommendation. `WAIM(2016)` **[RS]** **[[PDF](http://www.junminghuang.com/WAIM2016-yu.pdf)]**\n\n-\tTraining Region-Based Object Detectors With Online Hard Example Mining. `CVPR(2016)` **[CV]** **[[PDF](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Shrivastava_Training_Region-Based_Object_CVPR_2016_paper.pdf)]**\n\n-\tHard Negative Mining for Metric Learning Based Zero-Shot Classification. `ECCV(2016)` **[ML]** **[[PDF](https://link.springer.com/content/pdf/10.1007/978-3-319-49409-8_45.pdf)]**\n\n-\tVehicle detection in aerial images based on region convolutional neural networks and hard negative example mining. `Sensors(2017)` **[CV]** **[[PDF](https://www.mdpi.com/1424-8220/17/2/336/pdf)]**\n\n-\tWalkRanker: A Unified Pairwise Ranking Model with Multiple Relations for Item Recommendation. `AAAI(2018)` **[RS]** **[[PDF](https://ojs.aaai.org/index.php/AAAI/article/view/11866/11725)]**\n\n-\tBootstrapping Entity Alignment with Knowledge Graph Embedding. `IJCAI(2018)` **[KGE]** **[[PDF](https://www.ijcai.org/Proceedings/2018/0611.pdf)]**\n\n-\tImproving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors. `CVPR(2018)` **[CV]** **[[PDF](https://openaccess.thecvf.com/content_cvpr_2018/papers/Noh_Improving_Occlusion_and_CVPR_2018_paper.pdf)]**\n\n-\tNSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding. `ICDE(2019)` **[KGE]** **[[PDF](https://arxiv.org/pdf/1812.06410)]**\n\n-\tMeta-Transfer Learning for Few-Shot Learning. `CVPR(2019)` **[CV]** **[[PDF](http://openaccess.thecvf.com/content_CVPR_2019/papers/Sun_Meta-Transfer_Learning_for_Few-Shot_Learning_CVPR_2019_paper.pdf)]**\n\n-\tULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining. `ISBI(2019)` **[CV]** **[[PDF](https://arxiv.org/pdf/1901.06359.pdf)]**\n\n-\tDistributed representation learning via node2vec for implicit feedback recommendation. `NCA(2020)` **[NLP]** **[[PDF](https://link.springer.com/article/10.1007/s00521-018-03964-2)]**\n\n-\tSimplify and Robustify Negative Sampling for Implicit Collaborative Filtering. `arXiv(2020)`  **[RS]** **[[PDF](https://arxiv.org/pdf/2009.03376)]**\n\n-\tHard Negative Mixing for Contrastive Learning. `arXiv(2020)` **[CL]** **[[PDF](https://arxiv.org/pdf/2010.01028)]**\n\n-\tBundle Recommendation with Graph Convolutional Networks. `SIGIR(2020)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3397271.3401198)]**\n\n-\tSupervised Contrastive Learning. `NIPS(2020)` **[CL]** **[[PDF](https://arxiv.org/abs/2004.11362)]**\n\n-\tCurriculum Meta-Learning for Next POI Recommendation. `KDD(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3447548.3467132)]**\n\n-\tBoosting the Speed of Entity Alignment 10×: Dual Attention Matching Network with Normalized Hard Sample Mining. `WWW(2021)` **[KGE]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3442381.3449897)]**\n\n-\tHard-Negatives or Non-Negatives? A Hard-Negative Selection Strategy for Cross-Modal Retrieval Using the Improved Marginal Ranking Loss. `ICCV(2021)` **[CV]** **[[PDF](https://openaccess.thecvf.com/content/ICCV2021W/ViRaL/papers/Galanopoulos_Hard-Negatives_or_Non-Negatives_A_Hard-Negative_Selection_Strategy_for_Cross-Modal_Retrieval_ICCVW_2021_paper.pdf)]**\n\n-\tNeighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings. `EMNLP(2022)` **[NLP]** **[[PDF](https://arxiv.org/pdf/2202.06671)]**\n\n\n### Adversarial Sampling\n\n-\tDeep Generative Image Models using a Laplacian Pyramid of Adversarial Networks. `NIPS(2015)` **[CV]** **[[PDF](https://arxiv.org/pdf/1506.05751.pdf)]**\n\n-\tIRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models. `SIGIR(2017)` **[IR]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3077136.3080786)]**\n\n-\tSeqGAN: Sequence Generative Adversarial Nets with Policy Gradient. `AAAI(2017)` **[NLP]** **[[PDF](https://ojs.aaai.org/index.php/AAAI/article/view/10804/10663)]**\n\n-\tKBGAN: Adversarial Learning for Knowledge Graph Embeddings. `NAACL(2018)` **[KGE]** **[[PDF](https://www.aclweb.org/anthology/N18-1133.pdf)]**\n\n-\tNeural Memory Streaming Recommender Networks with Adversarial Training. `KDD(2018)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3219819.3220004)]**\n\n-\tGraphGAN: Graph Representation Learning with Generative Adversarial Nets. `AAAI(2018)` **[GRL]** **[[PDF](https://ojs.aaai.org/index.php/AAAI/article/download/11872/11731)]**\n\n-\tCFGAN: A Generic Collaborative Filtering Framework based on Generative Adversarial Networks. `CIKM(2018)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3269206.3271743)]**\n\n-\tAdversarial Contrastive Estimation. `ACL(2018)` **[NLP]** **[[PDF](https://arxiv.org/pdf/1805.03642)]**\n\n-\tIncorporating GAN for Negative Sampling in Knowledge Representation Learning. `AAAI(2018)` **[KGE]** **[[PDF](https://ojs.aaai.org/index.php/AAAI/article/download/11536/11395)]**\n\n-\tExploring the potential of conditional adversarial networks for optical and SAR image matching. `IEEE J-STARS(2018)` **[CV]** **[[PDF](https://elib.dlr.de/118413/1/FINAL%20VERSION_elib.pdf)]**\n\n-\tDeep Adversarial Metric Learning. `CVPR(2018)` **[CV]** **[[PDF](https://openaccess.thecvf.com/content_cvpr_2018/papers/Duan_Deep_Adversarial_Metric_CVPR_2018_paper.pdf)]**\n\n-\tAdversarial Detection with Model Interpretation. `KDD(2018)` **[ML]** **[[PDF](https://people.engr.tamu.edu/xiahu/papers/kdd18liu.pdf)]**\n\n-\tAdversarial Sampling and Training for Semi-Supervised Information Retrieval. `WWW(2019)` **[IR]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3308558.3313416)]**\n\n-\tDeep Adversarial Social Recommendation. `IJCAI(2019)` **[RS]** **[[PDF](https://www.ijcai.org/proceedings/2019/0187.pdf)]**\n\n-\tAdversarial Learning on Heterogeneous Information Networks. `KDD(2019)` **[HIN]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3292500.3330970)]**\n\n-\tRegularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction. `CIKM(2019)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3357384.3357936)]**\n\n-\tAdversarial Knowledge Representation Learning Without External Model. `IEEE Access(2019)` **[KGE]** **[[PDF](https://ieeexplore.ieee.org/iel7/6287639/6514899/08599182.pdf)]**\n\n-\tAdversarial Binary Collaborative Filtering for Implicit Feedback. `AAAI(2019)` **[RS]** **[[PDF](https://ojs.aaai.org/index.php/AAAI/article/download/4460/4338)]**\n\n-\tProGAN: Network Embedding via Proximity Generative Adversarial Network. `KDD(2019)` **[GRL]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3292500.3330866)]**\n\n-\tGenerating Fluent Adversarial Examples for Natural Languages. `ACL(2019)` **[NLP]** **[[PDF](https://www.aclweb.org/anthology/P19-1559.pdf)]**\n\n-\tIPGAN: Generating Informative Item Pairs by Adversarial Sampling. `TNLLS(2020)`  **[RS]** **[[PDF](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9240960)]**\n\n-\tContrastive Learning with Adversarial Examples. `arXiv(2020)` **[CL]** **[[PDF](https://arxiv.org/pdf/2010.12050)]**\n\n-\tPURE: Positive-Unlabeled Recommendation with Generative Adversarial Network. `KDD(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3447548.3467234)]**\n\n-\tNegative Sampling for Knowledge Graph Completion Based on Generative Adversarial Network. `ICCCI(2021)` **[KGE]** **[[PDF](https://link.springer.com/chapter/10.1007/978-3-030-88081-1_1)]**\n\n-\tSynthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation. `arXiv(2021)` **[NLP]** **[[PDF](https://arxiv.org/pdf/2106.05894)]**\n\n-\tAdversarial Feature Translation for Multi-domain Recommendation. `KDD(2021)` **[RS]** **[[PDF](http://nlp.csai.tsinghua.edu.cn/~xrb/publications/KDD-2021_AFT.pdf)]**\n\n-\tAdversarial training regularization for negative sampling based network embedding. `Information Sciences(2021)` **[GRL]** **[[PDF](https://doi.org/10.1016/j.ins.2021.07.018)]**\n\n-\tAdversarial Caching Training: Unsupervised Inductive Network Representation Learning on Large-Scale Graphs. `TNNLS(2021)` **[GRL]** **[[PDF](https://ieeexplore.ieee.org/abstract/document/9451538/)]**\n\n-\tA Robust and Generalized Framework for Adversarial Graph Embedding. `arxiv(2021)` **[GRL]** **[[PDF](https://arxiv.org/pdf/2105.10651)]**\n\n-\tInstance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation. `ICCV(2021)` **[CV]** **[[PDF](http://openaccess.thecvf.com/content/ICCV2021/papers/Wang_Instance-Wise_Hard_Negative_Example_Generation_for_Contrastive_Learning_in_Unpaired_ICCV_2021_paper.pdf)]**\n\n\n### Graph-based Sampling\n\n-\tACRec: a co-authorship based random walk model for academic collaboration recommendation. `WWW(2014)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2567948.2579034)]**\n\n-\tGNEG: Graph-Based Negative Sampling for word2vec. `ACL(2018)` **[NLP]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3219819.3219890)]**\n\n-\tGraph Convolutional Neural Networks for Web-Scale Recommender Systems. `KDD(2018)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3219819.3219890)]**\n\n-\tSamWalker: Social Recommendation with Informative Sampling Strategy. `WWW(2019)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3308558.3313582)]**\n\n-\tUnderstanding Negative Sampling in Graph Representation Learning. `KDD(2020)` **[GRL]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3394486.3403218)]**\n\n-\tReinforced Negative Sampling over Knowledge Graph for Recommendation. `WWW(2020)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3366423.3380098)]**\n\n-\tMixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems. `KDD(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3447548.3467408)]**\n\n-\tSamWalker++: recommendation with informative sampling strategy. `TKDE(2021)` **[RS]** **[[PDF](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9507306)]**\n\n-\tDSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN. `CIKM(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3459637.3482092)]**\n\n\n### Additional data enhanced Sampling\n\n-\tLeveraging Social Connections to Improve Personalized Ranking for Collaborative Filtering. `CIKM(2014)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2661829.2661998)]**\n\n-\tSocial Recommendation with Strong and Weak Ties. `CIKM(2016)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2983323.2983701)]**\n\n-\tBayesian Personalized Ranking with Multi-Channel User Feedback. `RecSys(2016)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/2959100.2959163)]**\n\n-\tJoint Geo-Spatial Preference and Pairwise Ranking for Point-of-Interest Recommendation. `ICTAI(2017)` **[RS]** **[[PDF](https://www.researchgate.net/profile/Fajie-Yuan/publication/308501951_Joint_Geo-Spatial_Preference_and_Pairwise_Ranking_for_Point-of-Interest_Recommendation/links/59bc0406aca272aff2d47bda/Joint-Geo-Spatial-Preference-and-Pairwise-Ranking-for-Point-of-Interest-Recommendation.pdf)]**\n\n-\tA Personalised Ranking Framework with Multiple Sampling Criteria for Venue Recommendation. `CIKM(2017)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3132847.3132985)]**\n\n-\tAn Improved Sampling for Bayesian Personalized Ranking by Leveraging View Data. `WWW(2018)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3184558.3186905)]**\n\n-\tReinforced Negative Sampling for Recommendation with Exposure Data. `IJCAI(2019)` **[RS]** **[[PDF](https://www.ijcai.org/Proceedings/2019/0309.pdf)]**\n\n-\tGeo-ALM: POI Recommendation by Fusing Geographical Information and Adversarial Learning Mechanism. `IJCAI(2019)` **[RS]** **[[PDF](https://www.ijcai.org/Proceedings/2019/0250.pdf)]**\n\n-\tBayesian Deep Learning with Trust and Distrust in Recommendation Systems. `WI(2019)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3350546.3352496)]**\n\n-\tSocially-Aware Self-Supervised Tri-Training for Recommendation. `arXiv(2021)` **[RS]** **[[PDF](https://arxiv.org/pdf/2106.03569)]**\n\n-\tDGCN: Diversified Recommendation with Graph Convolutional Networks. `WWW(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3442381.3449835)]**\n\n\nFuture Outlook\n----\n### False Negative Problem\n\n-\tIncremental False Negative Detection for Contrastive Learning. `arXiv(2021)` **[CL]** **[[PDF](https://arxiv.org/pdf/2106.03719)]**\n\n-\tGraph Debiased Contrastive Learning with Joint Representation Clustering. `IJCAI(2021)` **[GRL \u0026 CL]** **[[PDF](https://www.ijcai.org/proceedings/2021/0473.pdf)]**\n\n-\tRelation-aware Graph Attention Model With Adaptive Self-adversarial Training. `AAAI(2021)` **[KGE]** **[[PDF](https://www.aaai.org/AAAI21Papers/AAAI-5774.QinX.pdf)]**\n\n\n### Curriculum Learning\n\n-\tOn The Power of Curriculum Learning in Training Deep Networks. `ICML(2016)` **[CV]** **[[PDF](http://proceedings.mlr.press/v97/hacohen19a/hacohen19a.pdf)]**\n\n-\tGraph Representation with Curriculum Contrastive Learning. `IJCAI(2021)` **[GRL \u0026 CL]** **[[PDF](https://www.ijcai.org/proceedings/2021/0317.pdf)]**\n\n### Negative Sampling Ratio\n\n-\tAre all negatives created equal in contrastive instance discrimination. `arXiv(2020)` **[CL]** **[[PDF](https://arxiv.org/pdf/2010.06682)]**\n\n-\tSimpleX: A Simple and Strong Baseline for Collaborative Filtering. `CIKM(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3459637.3482297)]**\n\n-\tRethinking InfoNCE: How Many Negative Samples Do You Need. `arXiv(2021)` **[CL]** **[[PDF](https://arxiv.org/pdf/2105.13003.pdf)]**\n\n### Debiased Sampling\n\n-\tDebiased Contrastive Learning. `NIPS(2020)` **[CL]** **[[PDF](https://arxiv.org/pdf/2007.00224)]**\n\n-\tContrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems. `KDD(2021)` **[RS]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3447548.3467102)]**\n\n### Non-Sampling\n\n-\tBeyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition. `ICCV(2013)` **[CV]** **[[PDF](http://openaccess.thecvf.com/content_iccv_2013/papers/Henriques_Beyond_Hard_Negative_2013_ICCV_paper.pdf)]**\n\n-\tEfficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation. `AAAI(2020)` **[RS]** **[[PDF](https://ojs.aaai.org/index.php/AAAI/article/download/5329/5185)]**\n\n-\tEfficient Non-Sampling Knowledge Graph Embedding. `WWW(2021)` **[KGE]** **[[PDF](https://dl.acm.org/doi/pdf/10.1145/3442381.3449859)]**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRUCAIBox%2FNegative-Sampling-Paper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRUCAIBox%2FNegative-Sampling-Paper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRUCAIBox%2FNegative-Sampling-Paper/lists"}