SIGIR2021推荐系统论文集锦
嘿，记得给“机器学习与推荐算法”添加星标
第44届国际信息检索研究和发展大会（SIGIR）将于2021年7月11-15日在线上举行（目前正在进行中）。此次大会共收到了720篇长文投稿，录用151篇，长文录取率21%（去年的录取率为26.4%）；共收到了526篇短文投稿，录用145篇，短文录取率27%（去年的录取率为30%）。
正因为推荐与搜索是解决信息过载的两种有效途径，因此虽然是关于检索的会议，但推荐系统占据了很大比例，与信息搜索不相上下。本文对推荐系统相关的论文进行了整理。为了方便查看与了解，我们主要将其分为了以下几类：Collaborative Filtering、Privacy&Security in RS、Sequential RS、Graph-based RS、Explainable RS、Conversational RS、News RS、Social RS、Cross-domain RS、Attention based RS、Fair RS。
另外，以上分类仁者见仁，智者见智，目的是给大家一个相对清晰的结构。如果看的不过瘾，除了按照以上分类来进行展示外，我们还给出了按照长文和短文进行粗粒度分类的论文列表，以供大家进行更加全面的浏览相关idea以及按照自己的标准来进行分类。需要注意的是，文本涉及的论文中大部分提供了原论文的PDF阅读链接与源码链接。P.S. 更加详细与官方的论文列表如下：
https://sigir.org/sigir2021/accepted-papers/
Collaborative Filtering
Bootstrapping User and Item Representations for One-Class Collaborative Filtering --https://arxiv.org/abs/2105.06323
Neural Graph Matching based Collaborative Filtering (PDF)--https://arxiv.org/abs/2105.04067 (Code)--https://github.com/ruizhang-ai/GMCF_Neural_Graph_Matching_based_Collaborative_Filtering
Enhanced Graph Learning for Collaborative Filtering via Mutual Information Maximization
Privacy & Security in RS
A Study of Defensive Methods to Protect Visual Recommendation Against Adversarial Manipulation of Images --http://sisinflab.poliba.it/publications/2021/ADDMM21/SIGIR2021_A_Study_of_Defensive_Methods_to_Protect_Visual_Recommendation_Against_Adversarial_Manipulation_of_Images.pdf
Fight Fire with Fire: Towards Robust Recommender Systems via Adversarial Poisoning Training
Sequential Recommendation
Category-aware Collaborative Sequential Recommendation
Sequential Recommendation with Graph Convolutional Networks
StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking (PDF)--https://arxiv.org/abs/2012.07598 (Code)--https://github.com/wangjiachun0426/StackRec
Counterfactual Data-Augmented Sequential Recommendation
CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
Session-based Recommendation
Dual Attention Transfer in Session-based Recommendation with Multi Dimensional Integration
Unsupervised Proxy Selection for Session-based Recommender Systems
The World is Binary: Contrastive Learning for Denoising Next Basket Recommendation --https://github.com/QYQ-bot/CLEA
Graph-based Recommendation
Sequential Recommendation with Graph Convolutional Networks
Structured Graph Convolutional Networks with Stochastic Masks for Recommender Systems
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning --https://arxiv.org/abs/2105.09710
Neural Graph Matching based Collaborative Filtering (PDF)--https://arxiv.org/abs/2105.04067 (Code)--https://github.com/ruizhang-ai/GMCF_Neural_Graph_Matching_based_Collaborative_Filtering
Joint Knowledge Pruning and Recurrent Graph Convolution for News Recommendation --https://yuh-yang.github.io/resources/kopra.pdf
Privileged Graph Distillation for Cold-start Recommendation --https://arxiv.org/abs/2105.14975
Self-supervised Graph Learning for Recommendation (PDF)--https://arxiv.org/abs/2010.10783 (Code)--https://github.com/wujcan/SGL
Graph Meta Network for Multi-Behavior Recommendation with Interaction Heterogeneity and Diversity
Enhanced Graph Learning for Collaborative Filtering via Mutual Information Maximization
Explainable Recommendation
ReXPlug: Explainable Recommendation using Plug-and-Play Language Model
User-Centric Path Reasoning towards Explainable Recommendation
Conversational Recommendation
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning --https://arxiv.org/abs/2105.09710
Learning to Ask Appropriate Questions in Conversational Recommendation
Comparison-based Conversational Recommender System with Relative Bandit Feedback
News Recommendation
Personalized News Recommendation with Knowledge-aware News Interactions --https://arxiv.org/abs/2104.10083
Joint Knowledge Pruning and Recurrent Graph Convolution for News Recommendation --https://yuh-yang.github.io/resources/kopra.pdf
Social Recommendation
Social Recommendation with Implicit Social Influence
ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation (PDF)--https://arxiv.org/abs/2105.02254 (Code)--https://github.com/YangLiangwei/ConsisRec
Cross-domain Recommendation
Federated Collaborative Transfer for Cross-Domain Recommendation
Learning Domain Semantics and Cross-Domain Correlations for Paper Recommendation --http://splab.sdu.edu.cn/download/paper/SIGIR-Cross-210501.pdf
Attention & Transformer & BERT
Dual Attention Transfer in Session-based Recommendation with Multi Dimensional Integration
Package Recommendation with Intra- and Inter-Package Attention Networks --http://shichuan.org/doc/108.pdf
Self-supervised & Contrasive Learning
The World is Binary: Contrastive Learning for Denoising Next Basket Recommendation --https://github.com/QYQ-bot/CLEA
Self-supervised Graph Learning for Recommendation (PDF)--https://arxiv.org/abs/2010.10783 (Code)--https://github.com/wujcan/SGL
Cold-start Problem
FORM: Follow the Online Regularized Meta-Leader for Cold-Start Recommendation
Privileged Graph Distillation for Cold-start Recommendation --https://arxiv.org/abs/2105.14975
Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks --https://arxiv.org/abs/2105.04790
Fairness among New Items in Cold Start Recommender Systems --http://people.tamu.edu/~zhuziwei/pubs/Ziwei_SIGIR_2021.pdf
Bias & Fairness
AutoDebias: Learning to Debias for Recommendation (PDF)--https://arxiv.org/abs/2105.04170 (Code)--https://github.com/DongHande/AutoDebias
Personalized Counterfactual Fairness in Recommendation
Mitigating Sentiment Bias for Recommender Systems
TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers --https://arxiv.org/abs/2104.09024
Causal Intervention for Leveraging Popularity Bias in Recommendation (PDF)--http://staff.ustc.edu.cn/~hexn/papers/sigir21-PDA.pdf (Code)--https://github.com/zyang1580/PDA
Fairness among New Items in Cold Start Recommender Systems --http://people.tamu.edu/~zhuziwei/pubs/Ziwei_SIGIR_2021.pdf
以上为按照推荐系统研究问题进行分类展示，以下将列举出SIGIR2021上关于接收的关于推荐系统大领域的长文和短文的论文列表，供大家有选择的阅读。另外，大部分提供了论文的PDF阅读链接与源码链接。
Long Papers
[1] A Study of Defensive Methods to Protect Visual Recommendation Against Adversarial Manipulation of Images
http://sisinflab.poliba.it/publications/2021/ADDMM21/SIGIR2021_A_Study_of_Defensive_Methods_to_Protect_Visual_Recommendation_Against_Adversarial_Manipulation_of_Images.pdf
[2] On Interpretation and Measurement of Soft Attributes for Recommendation
https://storage.googleapis.com/pub-tools-public-publication-data/pdf/9466caf5c19edb6fb95cadb322baf4912c1a1866.pdf
[3] Category-aware Collaborative Sequential Recommendation
[4] DEKR: Description Enhanced Knowledge Graph for Machine Learning Method Recommendation
[5] Sequential Recommendation with Graph Convolutional Networks
[6] Dual Attention Transfer in Session-based Recommendation with Multi Dimensional Integration
[7] Structured Graph Convolutional Networks with Stochastic Masks for Recommender Systems
[8] AutoDebias: Learning to Debias for Recommendation
https://arxiv.org/abs/2105.04170)]
https://github.com/DongHande/AutoDebias
[9] Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation
https://arxiv.org/abs/2105.07377
[10] Learning Recommender Systems with Implicit Feedback via Soft Target Enhancement
[11] Unsupervised Proxy Selection for Session-based Recommender Systems
[12] Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
https://arxiv.org/abs/2105.09710
[13] ReXPlug: Explainable Recommendation using Plug-and-Play Language Model
[14] Bootstrapping User and Item Representations for One-Class Collaborative Filtering
https://arxiv.org/abs/2105.06323
[15] Package Recommendation with Intra- and Inter-Package Attention Networks
http://shichuan.org/doc/108.pdf
[16] When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution
https://arxiv.org/abs/2104.07150
[17] Path-based Deep Network for Candidate Item Matching in Recommenders
https://arxiv.org/abs/2105.08246
[18] New Insights into Metric Optimization for Ranking-based Recommendation
https://julian-urbano.info/files/publications/046-new-insights-metric-optimization-ranking-based-recommendation.pdf
https://github.com/roger-zhe-li/sigir21-newinsights
[19] Personalized Counterfactual Fairness in Recommendation
[20] Enhancing Domain-Level and User-Level Adaptivity in Diversified Recommendation
[21] Mitigating Sentiment Bias for Recommender Systems
[22] Federated Collaborative Transfer for Cross-Domain Recommendation
[23] Standing in Your Shoes: External Assessments for Personalized Recommender Systems
https://staff.fnwi.uva.nl/m.derijke/wp-content/papercite-data/pdf/lu-2021-standing.pdf
[24] Personalized News Recommendation with Knowledge-aware News Interactions
https://arxiv.org/abs/2104.10083
[25] The World is Binary: Contrastive Learning for Denoising Next Basket Recommendation
https://github.com/QYQ-bot/CLEA
[26] A Guided Learning Approach for Item Recommendation via Surrogate Loss Learning
[27] Learning to Ask Appropriate Questions in Conversational Recommendation
[28] Neural Graph Matching based Collaborative Filtering
https://arxiv.org/abs/2105.04067
https://github.com/ruizhang-ai/GMCF_Neural_Graph_Matching_based_Collaborative_Filtering
[29] FORM: Follow the Online Regularized Meta-Leader for Cold-Start Recommendation
[30] User-Centric Path Reasoning towards Explainable Recommendation
[31] Joint Knowledge Pruning and Recurrent Graph Convolution for News Recommendation
PDF](https://yuh-yang.github.io/resources/kopra.pdf
[32] StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
https://arxiv.org/abs/2012.07598
https://github.com/wangjiachun0426/StackRec
[33] Privileged Graph Distillation for Cold-start Recommendation
https://arxiv.org/abs/2105.14975
[34] Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue
https://arxiv.org/abs/2009.09945
[35] Counterfactual Data-Augmented Sequential Recommendation
[36] Fight Fire with Fire: Towards Robust Recommender Systems via Adversarial Poisoning Training
[37] Self-supervised Graph Learning for Recommendation
https://arxiv.org/abs/2010.10783
https://github.com/wujcan/SGL
[38] TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers
https://arxiv.org/abs/2104.09024
[39] Graph Meta Network for Multi-Behavior Recommendation with Interaction Heterogeneity and Diversity
[40] Learning Domain Semantics and Cross-Domain Correlations for Paper Recommendation
http://splab.sdu.edu.cn/download/paper/SIGIR-Cross-210501.pdf
[41] Comparison-based Conversational Recommender System with Relative Bandit Feedback
[42] Enhanced Graph Learning for Collaborative Filtering via Mutual Information Maximization
[43] CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
[44] Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback
[45] Causal Intervention for Leveraging Popularity Bias in Recommendation
http://staff.ustc.edu.cn/~hexn/papers/sigir21-PDA.pdf
https://github.com/zyang1580/PDA
[46] UGRec: Modeling Directed and Undirected Relations for Recommendation
https://arxiv.org/abs/2105.04183
[47] Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
https://arxiv.org/abs/2105.04790
[48] Fairness among New Items in Cold Start Recommender Systems
http://people.tamu.edu/~zhuziwei/pubs/Ziwei_SIGIR_2021.pdf
Short Papers
[1] Variational Autoencoders for Top-K Recommendation with Implicit Feedback
[2] Motif-aware Sequential Recommendation
[3] Lighter and Better: Low-Rank Decomposed Self-Attention Networks for Next-Item Recommendation
https://www.microsoft.com/en-us/research/uploads/prod/2021/05/LighterandBetter_Low-RankDecomposedSelf-AttentionNetworksforNext-ItemRecommendation.pdf
[4] The Winner Takes it All: Geographic Imbalance and Provider (Un)fairness in Educational Recommender Systems
[5] RMBERT:News Recommendation via Recurrent Reasoning Memory Network over BERT
[6] Entangled Bidirectional Encoder to Autoregressive Decoder for Sequential Recommendation
[7] Dual Unbiased Recommender Learning for Implicit Feedback
[8] Info-flow Enhanced GANs for Recommender
[9] Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer
https://arxiv.org/abs/2105.00522
https://github.com/DyGRec/ASReP
[10] Neural Representations in Hybrid Recommender Systems: Prediction versus Regularization
https://arxiv.org/abs/2010.06070
[11] Cluster-Based Bandits: Fast Cold-Start for Recommender System New Users
https://www.scss.tcd.ie/Doug.Leith/pubs/sigir16.pdf
[12] Social Recommendation with Implicit Social Influence
[13] Underestimation Refinement: A General Enhancement Strategy for Exploration in Recommendation Systems
[14] Counterfactual Explanations for Neural Recommenders
https://arxiv.org/abs/2105.05008
https://github.com/hieptk/accent
[15] Sequential Recommendation for Cold-start Users with Meta Transitional Learning
http://people.tamu.edu/~jwang713/pubs/MetaTL-sigir2021
[16] Cross-Batch Negative Sampling for Training Two-Tower Recommenders
[17] Empowering News Recommendation with Pre-trained Language Models
https://arxiv.org/abs/2104.07413
[18] Bayesian Critiquing with Keyphrase Activation Vectors for VAE-based Recommender Systems
https://ssanner.github.io/papers/sigir21_tcavcrit.pdf
[19] ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation
https://arxiv.org/abs/2105.02254
https://github.com/YangLiangwei/ConsisRec
[20] ICAI-SR: Item Categorical Attribute Integrated Sequential Recommendation
[21] AMM: Attentive Multi-field Matching for News Recommendation
[22] Temporal Augmented Graph Neural Networks for Session-Based Recommendations
[23] Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users
https://arxiv.org/abs/2105.0478
参考的Github仓库如下，欢迎支持与star。
1. https://github.com/hongleizhang/RSPapers
2. https://github.com/jihoo-kim/RecSys-Papers-from-SIGIR-2021
推荐阅读
喜欢的话点个在看吧👇