{"type":"ScholarlyArticle","title":"Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach","authors":[{"name":"Chenxiao Yang","slug":"chenxiao-yang","given":"Chenxiao","family":"Yang","affiliation":"MoE Key Lab of Artificial Intelligence , Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Qitian Wu","slug":"qitian-wu","given":"Qitian","family":"Wu","affiliation":"MoE Key Lab of Artificial Intelligence , Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Jipeng Jin","slug":"jipeng-jin","given":"Jipeng","family":"Jin","affiliation":"MoE Key Lab of Artificial Intelligence , Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Xiaofeng Gao","slug":"xiaofeng-gao","given":"Xiaofeng","family":"Gao","affiliation":"MoE Key Lab of Artificial Intelligence , Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Junwei Pan","slug":"junwei-pan","given":"Junwei","family":"Pan","affiliation":"Tencent Inc."},{"name":"Guihai Chen","slug":"guihai-chen","given":"Guihai","family":"Chen","affiliation":"MoE Key Lab of Artificial Intelligence , Department of Computer Science and Engineering , Shanghai Jiao Tong University"}],"abstract":"Collaborative filtering (CF), as a standard method for recommendation with implicit feedback, tackles a semi-supervised learning problem where most interaction data are unobserved. Such a nature makes existing approaches highly rely on mining negatives for providing correct training signals. However, mining proper negatives is not a free lunch, encountering with a tricky trade-off between mining informative hard negatives and avoiding false ones. We devise a new approach named as Hardness-Aware Debiased Contrastive Collaborative Filtering (HDCCF) to resolve the dilemma. It could sufficiently explore hard negatives from two-fold aspects: 1) adaptively sharpening the gradients of harder instances through a set-wise objective, and 2) implicitly leveraging item/user frequency information with a new sampling strategy. To circumvent false negatives, we develop a principled approach to improve the reliability of negative instances and prove that the objective is an unbiased estimation of sampling from the true negative distribution. Extensive experiments demonstrate the superiority of the proposed model over existing CF models and hard negative mining methods.","doi":"10.24963/ijcai.2022/327","url":"https://ijcai.org/proceedings/2022/327","pdf":"https://ijcai.org/proceedings/2022/0327.pdf","markdown":"https://ijcai.org/proceedings/2022/327.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/327","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":327,"pages":{"first":2355,"last":2361},"keywords":["Data Mining: Collaborative Filtering","Data Mining: Information Retrieval","Data Mining: Recommender Systems"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986587","length_sec":77,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984730","length_sec":351,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen et al., 2017] Ting Chen, Yizhou Sun, Yue Shi, and Liangjie Hong. On sampling strategies for neural network-based collabo- rative filtering. In SIGKDD, 2017.","title":"On sampling strategies for neural network-based collaborative filtering","authors":"Ting Chen, Yizhou Sun, Yue Shi, Liangjie Hong","year":"2017","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2020] Chong Chen, Min Zhang, Yongfeng Zhang, Yiqun Liu, and Shaoping Ma. Efficient neural matrix factoriza- tion without sampling for recommendation. TOIS, 38(2), 2020.","title":"Efficient neural matrix factorization without sampling for recommendation","authors":"Chong Chen, Min Zhang, Yongfeng Zhang, Yiqun Liu, Shaoping Ma","year":"2020","venue":"TOIS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cho et al., 2011] Eunjoon Cho, Seth A Myers, and Jure Leskovec. Friendship and mobility: user movement in location-based social networks. In SIGKDD, 2011.","title":"Friendship and mobility: user movement in location-based social networks","authors":"Cho","year":"2011","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ding et al., 2018] Jingtao Ding, Fuli Feng, Xiangnan He, Guanghui Yu, Yong Li, and Depeng Jin. An improved sampler for bayesian personalized ranking by leveraging view data. In WWW Companion, 2018.","title":"An improved sampler for bayesian personalized ranking by leveraging view data","authors":"Jingtao Ding, Fuli Feng, Xiangnan He, Guanghui Yu, Yong Li, Depeng Jin","year":"2018","venue":"WWW Companion","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ding et al., 2019] Jingtao Ding, Yuhan Quan, Xiangnan He, Yong Li, and Depeng Jin. Reinforced negative sampling for recom- mendation with exposure data. In IJCAI, 2019.","title":"Reinforced negative sampling for recommendation with exposure data","authors":"Jingtao Ding, Yuhan Quan, Xiangnan He, Yong Li, Depeng Jin","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/309"},{"position":6,"raw":"[Harper and Konstan, 2015] F Maxwell Harper and Joseph A Kon- stan. The movielens datasets: History and context. In ACM TiiS, 2015.","title":"The movielens datasets: History and context","authors":"Maxwell Harper, Joseph A Konstan","year":"2015","venue":"ACM TiiS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] Xiangnan He, Hanwang Zhang, Min-Yen Kan, and Tat-Seng Chua. Fast matrix factorization for online recom- mendation with implicit feedback. In SIGIR, 2016.","title":"Fast matrix factorization for online recommendation with implicit feedback","authors":"He","year":"2016","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2017] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. In WWW, pages 173-182, 2017.","title":"Neural collaborative filtering","authors":"He","year":"2017","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hernández-Lobato et al., 2014] José Miguel Hernández-Lobato, Neil Houlsby, and Zoubin Ghahramani. Probabilistic matrix fac- torization with non-random missing data. In ICML, 2014.","title":"Zoubin Ghahramani. Probabilistic matrix factorization with non-random missing data","authors":"Hernández-Lobato","year":"2014","venue":"José Miguel Hernández","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hsieh et al., 2017] Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge Belongie, and Deborah Estrin. Collabora- tive metric learning. In WWW, pages 193-201, 2017.","title":"Collaborative metric learning","authors":"Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge Belongie, Deborah Estrin","year":"2017","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jin et al., 2020] Binbin Jin, Defu Lian, Zheng Liu, Qi Liu, Jian- hui Ma, Xing Xie, and Enhong Chen. Sampling-decomposable generative adversarial recommender. In NeurIPS, 2020.","title":"Sampling-decomposable generative adversarial recommender","authors":"Binbin Jin, Defu Lian, Zheng Liu, Qi Liu, Jianhui Ma, Xing Xie, Enhong Chen","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kabbur et al., 2013] Santosh Kabbur, Xia Ning, and George Karypis. Fism: factored item similarity models for top-n rec- ommender systems. In SIGKDD, pages 659-667, 2013.","title":"Fism: factored item similarity models for top-n recommender systems","authors":"Santosh Kabbur, Xia Ning, George Karypis","year":"2013","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kang and McAuley, 2018] Wang-Cheng Kang and Julian McAuley. Self-attentive sequential recommendation. In ICDM, 2018.","title":"Self-attentive sequential recommendation","authors":"Wang-Cheng Kang, Julian Mcauley","year":"2018","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Koren et al., 2009] Yehuda Koren, Robert Bell, and Chris Volin- sky. Matrix factorization techniques for recommender systems. In Computer, pages 30-37, 2009.","title":"Matrix factorization techniques for recommender systems","authors":"Koren","year":"2009","venue":"Computer","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Koren, 2008] Yehuda Koren. Factorization meets the neighbor- hood: a multifaceted collaborative filtering model. In SIGKDD, 2008.","title":"Factorization meets the neighborhood: a multifaceted collaborative filtering model","authors":"Koren ;, Yehuda Koren","year":"2008","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ma et al., 2008] Hao Ma, Haixuan Yang, Michael R Lyu, and Ir- win King. Sorec: social recommendation using probabilistic ma- trix factorization. In CIKM, 2008.","title":"Sorec: social recommendation using probabilistic matrix factorization","authors":"Hao Ma, Haixuan Yang, Irwin Michael R Lyu, King","year":"2008","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ma et al., 2018] Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H Chi. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In SIGKDD, pages 1930-1939, 2018.","title":"Modeling task relationships in multi-task learning with multi-gate mixture-of-experts","authors":"Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, Ed H Chi","year":"2018","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Mnih and Salakhutdinov, 2007] Andriy Mnih and Russ R Salakhutdinov. Probabilistic matrix factorization. In NeurIPS, 2007. [Mnih and Salakhutdinov, 2008] Andriy Mnih and Russ R Salakhutdinov. Probabilistic matrix factorization. In NeurIPS, pages 1257-1264, 2008.","title":"Probabilistic matrix factorization","authors":"Andriy Mnih, Russ R Salakhutdinov","year":"2007","venue":"Andriy Mnih and Russ R Salakhutdinov. Probabilistic matrix factorization","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pan et al., 2008] Rong Pan, Yunhong Zhou, Bin Cao, Nathan N Liu, Rajan Lukose, Martin Scholz, and Qiang Yang. One-class collaborative filtering. In ICDM, 2008.","title":"One-class collaborative filtering","authors":"Rong Pan, Yunhong Zhou, Bin Cao, Nathan N Liu, Rajan Lukose, Martin Scholz, Qiang Yang","year":"2008","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Park and Chang, 2019] Dae Hoon Park and Yi Chang. Adversarial sampling and training for semi-supervised information retrieval. In WWW, 2019.","title":"Adversarial sampling and training for semi-supervised information retrieval","authors":"Dae Hoon, Park, Yi Chang","year":"2019","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rendle and Freudenthaler, 2014] Steffen Rendle and Christoph Freudenthaler. Improving pairwise learning for item recommen- dation from implicit feedback. In WSDM, 2014.","title":"Improving pairwise learning for item recommendation from implicit feedback","authors":"Steffen Rendle, Christoph Freudenthaler","year":"2014","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rendle et al., 2009] Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian person- alized ranking from implicit feedback. In UAI, pages 452-461, 2009.","title":"Bpr: Bayesian personalized ranking from implicit feedback","authors":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars Schmidt-Thieme","year":"2009","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Robinson et al., 2021] Joshua Robinson, Ching-Yao Chuang, Su- vrit Sra, and Stefanie Jegelka. Contrastive learning with hard negative samples. ICLR, 2021.","title":"Contrastive learning with hard negative samples","authors":"Joshua Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sarwar et al., 2001] Badrul Sarwar, George Karypis, Joseph Kon- stan, and John Riedl. Item-based collaborative filtering recom- mendation algorithms. In WWW, pages 285-295, 2001.","title":"Item-based collaborative filtering recommendation algorithms","authors":"Badrul Sarwar, George Karypis, Joseph Konstan, John Riedl","year":"2001","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shu et al., 2019] Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, and Deyu Meng. Meta-weight-net: Learning an explicit mapping for sample weighting. NeurIPS, 2019.","title":"Meta-weight-net: Learning an explicit mapping for sample weighting","authors":"Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, Deyu Meng","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Tay et al., 2018] Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. La- tent relational metric learning via memory-based attention for collaborative ranking. In WWW, pages 729-739, 2018.","title":"Latent relational metric learning via memory-based attention for collaborative ranking","authors":"Yi Tay, Anh Luu, Siu Tuan, Hui Cheung","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang and Liu, 2021] Feng Wang and Huaping Liu. Understanding the behaviour of contrastive loss. In CVPR, pages 2495-2504, 2021.","title":"Understanding the behaviour of contrastive loss","authors":"Wang, Liu ; ] Feng Wang, Huaping Liu","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2017] Jun Wang, Lantao Yu, Weinan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, and Dell Zhang. Irgan: A minimax game for unifying generative and discriminative information retrieval models. In SIGIR, pages 515-524, 2017.","title":"Irgan: A minimax game for unifying generative and discriminative information retrieval models","authors":"Jun Wang, Lantao Yu, Weinan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, Dell Zhang","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wu et al., 2017] Chao-Yuan Wu, R Manmatha, Alexander J Smola, and Philipp Krahenbuhl. Sampling matters in deep em- bedding learning. In ICCV, 2017.","title":"Sampling matters in deep embedding learning","authors":"Chao-Yuan, R Wu, Alexander J Manmatha, Philipp Smola, Krahenbuhl","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wu et al., 2018] Liwei Wu, Cho-Jui Hsieh, and James Sharpnack. Sql-rank: A listwise approach to collaborative ranking. In ICML, 2018.","title":"Sql-rank: A listwise approach to collaborative ranking","authors":"Liwei Wu, Cho-Jui Hsieh, James Sharpnack","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wu et al., 2019a] Ga Wu, Maksims Volkovs, Chee Loong Soon, Scott Sanner, and Himanshu Rai. Noise contrastive estimation for one-class collaborative filtering. In SIGIR, 2019.","title":"Noise contrastive estimation for one-class collaborative filtering","authors":"Wu","year":"2019","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Wu et al., 2019b] Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao, and Guihai Chen. Dual graph attention networks for deep latent representation of multifaceted social ef- fects in recommender systems. In WWW, 2019.","title":"Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems","authors":"Wu","year":"2019","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wu et al., 2021] Qitian Wu, Chenxiao Yang, Shuodian Yu, Xi- aofeng Gao, and Guihai Chen. Seq2bubbles: Region-based em- bedding learning for user behaviors in sequential recommenders. In CIKM, 2021.","title":"Seq2bubbles: Region-based embedding learning for user behaviors in sequential recommenders","authors":"Qitian Wu, Chenxiao Yang, Shuodian Yu, Xiaofeng Gao, Guihai Chen","year":"2021","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Yang et al., 2022] Chenxiao Yang, Junwei Pan, Xiaofeng Gao, Tingyu Jiang, Dapeng Liu, and Guihai Chen. Cross-task knowl- edge distillation in multi-task recommendation. AAAI, 2022.","title":"Cross-task knowledge distillation in multi-task recommendation","authors":"Yang","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}