ABSTRACT
Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems. Standard approaches approximate maximum likelihood estimation (MLE) through sampling for better scalability and address the problem of DCG in a way similar to language modeling. However, live recommender systems face severe exposure bias and have a vocabulary several orders of magnitude larger than that of natural language, implying that MLE will preserve and even exacerbate the exposure bias in the long run in order to faithfully fit the observed samples. In this paper, we theoretically prove that a popular choice of contrastive loss is equivalent to reducing the exposure bias via inverse propensity weighting, which provides a new perspective for understanding the effectiveness of contrastive learning. Based on the theoretical discovery, we design CLRec, a contrastive learning method to improve DCG in terms of fairness, effectiveness and efficiency in recommender systems with extremely large candidate size. We further improve upon CLRec and propose Multi-CLRec, for accurate multi-intention aware bias reduction. Our methods have been successfully deployed in Taobao, where at least four-month online A/B tests and offline analyses demonstrate its substantial improvements, including a dramatic reduction in the Matthew effect.
- Mart'in Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. Tensorflow: A system for large-scale machine learning. In OSDI. 265--283.Google Scholar
- Gediminas Adomavicius and YoungOk Kwon. 2011. Improving aggregate recommendation diversity using ranking-based techniques. TKDE (2011).Google Scholar
- Qingyao Ai, Keping Bi, Cheng Luo, Jiafeng Guo, and W Bruce Croft. 2018. Unbiased learning to rank with unbiased propensity estimation. In SIGIR. 385--394.Google Scholar
- Jinze Bai, Chang Zhou, Junshuai Song, Xiaoru Qu, Weiting An, Zhao Li, and Jun Gao. 2019. Personalized Bundle List Recommendation. In WWW. 60--71.Google Scholar
- Yoshua Bengio, Nicholas Lé onard, and Aaron C. Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. arXiv preprint arXiv:1308.3432 (2013).Google Scholar
- Yoshua Bengio and Jean-Sébastien Senécal. 2008. Adaptive importance sampling to accelerate training of a neural probabilistic language model. IEEE Trans. Neural Networks, Vol. 19, 4 (2008), 713--722.Google ScholarDigital Library
- Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Li Wei, Yi Wu, Lukasz Heldt, Zhe Zhao, Lichan Hong, Ed H. Chi, and Cristos Goodrow. 2019. Fairness in Recommendation Ranking through Pairwise Comparisons. In SIGKDD.Google ScholarDigital Library
- Robin Burke. 2017. Multisided Fairness for Recommendation. arxiv: 1707.00093 [cs.CY]Google Scholar
- Hugo Caselles-Dupré, Florian Lesaint, and Jimena Royo-Letelier. 2018. Word2vec applied to recommendation: Hyperparameters matter. In RecSys. ACM, 352--356.Google Scholar
- Minmin Chen, Alex Beutel, Paul Covington, Sagar Jain, Francois Belletti, and Ed H Chi. 2019. Top-k off-policy correction for a REINFORCE recommender system. In WSDM. 456--464.Google Scholar
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020).Google Scholar
- Ting Chen, Yizhou Sun, Yue Shi, and Liangjie Hong. 2017. On sampling strategies for neural network-based collaborative filtering. In SIGKDD.Google Scholar
- Xu Chen, Hongteng Xu, Yongfeng Zhang, Jiaxi Tang, Yixin Cao, Zheng Qin, and Hongyuan Zha. 2018. Sequential recommendation with user memory networks. In WSDM. 108--116.Google Scholar
- Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep neural networks for youtube recommendations. In RecSys. ACM, 191--198.Google Scholar
- Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In AISTATS. 249--256.Google Scholar
- Mihajlo Grbovic and Haibin Cheng. 2018. Real-time personalization using embeddings for search ranking at airbnb. In SIGKDD.Google Scholar
- Michael Gutmann and Aapo Hyv"arinen. 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In AISTATS. 297--304.Google Scholar
- Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2019. Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019).Google Scholar
- Yue He, Peng Cui, Jianxin Ma, Hao Zou, Xiaowei Wang, Hongxia Yang, and Philip S. Yu. 2020. Learning Stable Graphs from Multiple Environments with Selection Bias. In SIGKDD.Google Scholar
- Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015).Google Scholar
- R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, and Yoshua Bengio. 2018. Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018).Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780.Google Scholar
- Guido W Imbens and Donald B Rubin. 2015. Causal inference in statistics, social, and biomedical sciences .Cambridge University Press.Google ScholarDigital Library
- Sébastien Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio. 2014. On using very large target vocabulary for neural machine translation. arXiv preprint arXiv:1412.2007 (2014).Google Scholar
- Manas R Joglekar, Cong Li, Jay K Adams, Pranav Khaitan, and Quoc V Le. 2019. Neural input search for large scale recommendation models. arXiv preprint arXiv:1907.04471 (2019).Google Scholar
- Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2017. Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734 (2017).Google Scholar
- Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recommendation. In ICDM. IEEE, 197--206.Google Scholar
- Thomas Kipf, Elise van der Pol, and Max Welling. 2019. Contrastive Learning of Structured World Models. arXiv preprint arXiv:1911.12247 (2019).Google Scholar
- Yehuda Koren. 2008. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In SIGKDD.Google Scholar
- Chao Li, Zhiyuan Liu, Mengmeng Wu, Yuchi Xu, Huan Zhao, Pipei Huang, Guoliang Kang, Qiwei Chen, Wei Li, and Dik Lun Lee. 2019. Multi-interest network with dynamic routing for recommendation at Tmall. In CIKM.Google Scholar
- Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman, and Tony Jebara. 2018. Variational Autoencoders for Collaborative Filtering. In WWW.Google Scholar
- Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos, Mo Yu, Bing Xiang, Bowen Zhou, and Yoshua Bengio. 2017. A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017).Google Scholar
- Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, and Wenwu Zhu. 2019. Learning disentangled representations for recommendation. In NeurIPS. 5712--5723.Google Scholar
- Jianxin Ma, Chang Zhou, Hongxia Yang, Peng Cui, Xin Wang, and Wenwu Zhu. 2020. Disentangled Self-Supervision in Sequential Recommenders. In SIGKDD.Google Scholar
- Andrew McCallum, Kamal Nigam, et al. 1998. A comparison of event models for naive bayes text classification. In AAAI-98 workshop on learning for text categorization. Citeseer, 41--48.Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NeurIPS. 3111--3119.Google Scholar
- Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018).Google Scholar
- Kan Ren, Jiarui Qin, Yuchen Fang, Weinan Zhang, Lei Zheng, Weijie Bian, Guorui Zhou, Jian Xu, Yong Yu, Xiaoqiang Zhu, et al. 2019. Lifelong sequential modeling with personalized memorization for user response prediction. In SIGIR. 565--574.Google Scholar
- Paul R Rosenbaum and Donald B Rubin. 1983. The central role of the propensity score in observational studies for causal effects. Biometrika, Vol. 70, 1 (1983), 41--55.Google ScholarCross Ref
- Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. arXiv preprint arXiv:1602.05352 (2016).Google ScholarDigital Library
- Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In NeurIPS. 1857--1865.Google Scholar
- Harald Steck. 2013. Evaluation of recommendations: rating-prediction and ranking. In RecSys. 213--220.Google Scholar
- Stergios Stergiou, Zygimantas Straznickas, Rolina Wu, and Kostas Tsioutsiouliklis. 2017. Distributed negative sampling for word embeddings. In AAAI.Google Scholar
- Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, and Peng Jiang. 2019. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In CIKM. 1441--1450.Google Scholar
- Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM. 565--573.Google Scholar
- Steven K. Thompson. 2012. Sampling .Wiley.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. arXiv preprint arXiv:1706.03762 (2017).Google Scholar
- Petar Velivc ković, William Fedus, William L Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm. 2018. Deep graph infomax. arXiv preprint arXiv:1809.10341 (2018).Google Scholar
- Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. 2018. Cosface: Large margin cosine loss for deep face recognition. In CVPR. 5265--5274.Google Scholar
- Xuanhui Wang, Michael Bendersky, Donald Metzler, and Marc Najork. 2016. Learning to rank with selection bias in personal search. In SIGIR. 115--124.Google Scholar
- Nicolai Wojke and Alex Bewley. 2018. Deep cosine metric learning for person re-identification. In WACV. IEEE, 748--756.Google Scholar
- Longqi Yang, Yin Cui, Yuan Xuan, Chenyang Wang, Serge Belongie, and Deborah Estrin. 2018. Unbiased offline recommender evaluation for missing-not-at-random implicit feedback. In RecSys. 279--287.Google Scholar
- Haochao Ying, Fuzhen Zhuang, Fuzheng Zhang, Yanchi Liu, Guandong Xu, Xing Xie, Hui Xiong, and Jian Wu. 2018b. Sequential recommender system based on hierarchical attention network. In IJCAI.Google Scholar
- Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L Hamilton, and Jure Leskovec. 2018a. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. arXiv preprint arXiv:1806.01973 (2018).Google Scholar
- Shengyu Zhang, Dong Yao, Zhou Zhao, Tat-Seng Chua, and Fei Wu. 2021. CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation. In SIGIR.Google Scholar
- Chang Zhou, Jinze Bai, Junshuai Song, Xiaofei Liu, Zhengchao Zhao, Xiusi Chen, and Jun Gao. 2018. ATRank: An attention-based user behavior modeling framework for recommendation. In AAAI.Google Scholar
- Chang Zhou, Yuqiong Liu, Xiaofei Liu, Zhongyi Liu, and Jun Gao. 2017. Scalable graph embedding for asymmetric proximity. In AAAI.Google Scholar
- Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, and Kun Gai. 2019. Deep interest evolution network for click-through rate prediction. In AAAI, Vol. 33. 5941--5948.Google ScholarDigital Library
- Han Zhu, Xiang Li, Pengye Zhang, Guozheng Li, Jie He, Han Li, and Kun Gai. 2018. Learning Tree-based Deep Model for Recommender Systems. In SIGKDD.Google Scholar
- Rong Zhu, Kun Zhao, Hongxia Yang, Wei Lin, Chang Zhou, Baole Ai, Yong Li, and Jingren Zhou. 2019. AliGraph: a comprehensive graph neural network platform. VLDB, Vol. 12, 12 (2019), 2094--2105.Google ScholarDigital Library
- Hao Zou, Peng Cui, Bo Li, Zheyan Shen, Jianxin Ma, Hongxia Yang, and Yue He. 2020. Counterfactual Prediction for Bundle Treatment. In NeurIPS.Google Scholar
Index Terms
- Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems
Recommendations
Multi-view Contrastive Learning Network for Recommendation
Pattern Recognition and Computer VisionAbstractKnowledge graphs (KGs) are being introduced into recommender systems in more and more scenarios. However, the supervised signals of the existing KG-aware recommendation models only come from the historical interactions between users and items, ...
Contrastive Collaborative Filtering for Cold-Start Item Recommendation
WWW '23: Proceedings of the ACM Web Conference 2023The cold-start problem is a long-standing challenge in recommender systems. As a promising solution, content-based generative models usually project a cold-start item’s content onto a warm-start item embedding to capture collaborative signals from item ...
Enhanced contrastive learning with multi-aspect information for recommender systems
AbstractIn recent years, graph neural networks (GNNs), as the state-of-the-art technology have advanced the solutions of recommender systems (RSs). However, the representations of nodes obtained from GNN-based models are always suboptimal when ...
Highlights- Contrastive learning between nodes is promoted to alleviate the data sparsity.
- ...
Comments