{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:22:06Z","timestamp":1785543726491,"version":"3.56.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T00:00:00Z","timestamp":1744243200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Heilongjiang Key R&D Program of China","award":["GA23A915"],"award-info":[{"award-number":["GA23A915"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072136"],"award-info":[{"award-number":["62072136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>Negative sampling plays a crucial role in implicit-feedback-based collaborative filtering, where it leverages massive unlabeled data to generate negative signals for guiding supervised learning. The current state-of-the-art approaches focus on utilizing hard negative samples that contain more information to establish a better decision boundary. To strike a balance between efficiency and effectiveness, most existing methods adopt a two-pass approach: In the first pass, a fixed number of unobserved items are sampled using a simple static distribution, while, in the second pass, a more sophisticated negative sampling strategy is employed to select the final negative items. However, selecting negative samples solely from the original items in a dataset is inherently restricted due to the limited available choices and thus may not be able to effectively contrast positive samples. In this article, we empirically validate this observation through meticulously designed experiments and identify three major limitations of existing solutions: ambiguous trap, information discrimination, and false-negative samples.<\/jats:p>\n          <jats:p>\n            Our response to such limitations is to introduce \u201cdenoised\u201d and \u201caugmented\u201d negative samples that may not exist in the original dataset. This direction renders a few substantial technical challenges. First, constructing augmented negative samples may introduce excessive noise that eventually distorts the decision boundary. Second, the scarcity of supervision signals hampers the denoising process. To this end, we introduce, to the best of our knowledge, a novel generic denoising and augmented negative sampling paradigm and provide a concrete instantiation. First, we disentangle the hard and easy factors of negative items. Then, we regulate the augmentation of easy factors by carefully considering the direction and magnitude. Next, we propose a reverse attention mechanism to learn a user\u2019s negative preference, which allows us to perform a dimension-level denoising procedure on hard factors. Finally, we design an advanced negative sampling strategy to identify the final negative samples, taking into account both the score function used in existing methods and, to the best of our knowledge, a novel metric called synthesization gain. Through extensive experiments on real-world datasets, we demonstrate that our method substantially outperforms state-of-the-art baselines. Our code is publicly available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"url\" xlink:href=\"https:\/\/github.com\/Asa9aoTK\/ANS-Recbole\">https:\/\/github.com\/Asa9aoTK\/ANS-Recbole<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3690656","type":"journal-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T10:25:15Z","timestamp":1724840715000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Denoising and Augmented Negative Sampling for Collaborative Filtering"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1427-4139","authenticated-orcid":false,"given":"Yuhan","family":"Zhao","sequence":"first","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3853-6308","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9390-8234","authenticated-orcid":false,"given":"Riwei","family":"Lai","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5185-8387","authenticated-orcid":false,"given":"Qilong","family":"Han","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6132-5843","authenticated-orcid":false,"given":"Hongtao","family":"Song","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5842-838X","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,10]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Yu Bai Sally Goldman and Li Zhang. 2017. Tapas: Two-pass approximate adaptive sampling for softmax. Retrieved from https:\/\/arxiv.org\/abs\/1707.03073"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.912312"},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Jiawei Chen Hande Dong Xiang Wang Fuli Feng Meng Wang and Xiangnan He. 2023. Bias and debias in recommender system: A survey and future directions. ACM Transactions on Information Systems 41 3 (2023) 1\u201339.","DOI":"10.1145\/3564284"},{"key":"e_1_3_1_5_2","first-page":"1997","volume-title":"Proceedings of the ACM Web Conference","author":"Chen Jin","year":"2022","unstructured":"Jin Chen, Defu Lian, Binbin Jin, Kai Zheng, and Enhong Chen. 2022. Learning recommenders for implicit feedback with importance resampling. In Proceedings of the ACM Web Conference. 1997\u20132005."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5330"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098202"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546761"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498519"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186905"},{"key":"e_1_3_1_11_2","first-page":"2230","volume-title":"International Joint Conference on Artificial Intelligence","author":"Ding Jingtao","year":"2019","unstructured":"Jingtao Ding, Yuhan Quan, Xiangnan He, Yong Li, and Depeng Jin. 2019. Reinforced negative sampling for recommendation with exposure data. In International Joint Conference on Artificial Intelligence. 2230\u20132236."},{"key":"e_1_3_1_12_2","first-page":"1094","article-title":"Simplify and robustify negative sampling for implicit collaborative filtering","author":"Ding Jingtao","year":"2020","unstructured":"Jingtao Ding, Yuhan Quan, Quanming Yao, Yong Li, and Depeng Jin. 2020. Simplify and robustify negative sampling for implicit collaborative filtering. In Proceedings of the 34th International Conference on Neural Information Processing Systems.ACM, New York, NY, 1094\u20131105.","journal-title":"."},{"issue":"2","key":"e_1_3_1_13_2","first-page":"667","article-title":"Sampler design for bayesian personalized ranking by leveraging view data","volume":"33","author":"Ding Jingtao","year":"2019","unstructured":"Jingtao Ding, Guanghui Yu, Xiangnan He, Fuli Feng, Yong Li, and Depeng Jin. 2019. Sampler design for bayesian personalized ranking by leveraging view data. IEEE Trans. Knowl. Data Eng. 33, 2 (2019), 667\u2013681.","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"e_1_3_1_14_2","first-page":"249","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_1_16_2","first-page":"2058","volume-title":"Proceedings of the ACM Web Conference","author":"Han Tengyue","year":"2022","unstructured":"Tengyue Han, Pengfei Wang, Shaozhang Niu, and Chenliang Li. 2022. Modality matches modality: Pretraining modality-disentangled item representations for recommendation. In Proceedings of the ACM Web Conference. 2058\u20132066."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209981"},{"key":"e_1_3_1_19_2","first-page":"173","volume-title":"Proceedings of the ACM Web Conference","author":"He Xiangnan","year":"2017","unstructured":"Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In Proceedings of the ACM Web Conference. 173\u2013182."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467408"},{"key":"e_1_3_1_21_2","unstructured":"Yannis Kalantidis Mert Bulent Sariyildiz Noe Pion Philippe Weinzaepfel and Diane Larlus. 2020. Hard negative mixing for contrastive learning. In Proceedings of the 34th International Conference on Neural Information Processing Systems. ACM New York NY 21798\u201321809."},{"key":"e_1_3_1_22_2","first-page":"1965","volume-title":"Proceedings of the ACM Web Conference","author":"Kang SeongKu","year":"2022","unstructured":"SeongKu Kang, Dongha Lee, Wonbin Kweon, Junyoung Hwang, and Hwanjo Yu. 2022. Consensus learning from heterogeneous objectives for one-class collaborative filtering. In Proceedings of the ACM Web Conference. 1965\u20131976."},{"key":"e_1_3_1_23_2","unstructured":"Prannay Khosla Piotr Teterwak Chen Wang Aaron Sarna Yonglong Tian Phillip Isola Aaron Maschinot Ce Liu and Dilip Krishnan. 2020. Supervised contrastive learning. In Proceedings of the 34th International Conference on Neural Information Processing Systems.. ACM New York NY 18661\u201318673."},{"key":"e_1_3_1_24_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_1_26_2","unstructured":"Weiming Liu Jiajie Su Chaochao Chen and Xiaolin Zheng. 2021. Leveraging distribution alignment via stein path for cross-domain cold-start recommendation. In Proceedings of the 35th International Conference on Neural Information Processing Systems. ACM New York NY 19223\u201319234."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482297"},{"key":"e_1_3_1_28_2","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the International Conference on Neural Information Processing Systems. ACM New York NY."},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313416"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591665"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556248"},{"key":"e_1_3_1_32_2","first-page":"452","volume-title":"Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian Personalized Ranking from implicit feedback. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. AUAI Press, 452\u2013461."},{"key":"e_1_3_1_33_2","first-page":"1670","volume-title":"International Conference on Machine Learning","author":"Schnabel Tobias","year":"2016","unstructured":"Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In International Conference on Machine Learning. 1670\u20131679."},{"key":"e_1_3_1_34_2","first-page":"812","volume-title":"Proceedings of the ACM Web Conference","author":"Shi Wentao","year":"2023","unstructured":"Wentao Shi, Jiawei Chen, Fuli Feng, Jizhi Zhang, Junkang Wu, Chongming Gao, and Xiangnan He. 2023. On the theories behind hard negative sampling for recommendation. In Proceedings of the ACM Web Conference. 812\u2013822."},{"key":"e_1_3_1_35_2","unstructured":"Akash Srivastava Lazar Valkov Chris Russell Michael U Gutmann and Charles Sutton. 2017. Veegan: Reducing mode collapse in gans using implicit variational learning. In Proceedings of the International Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_36_2","first-page":"1","volume-title":"International Joint Conference on Neural Networks","author":"Thanh-Tung Hoang","year":"2020","unstructured":"Hoang Thanh-Tung and Truyen Tran. 2020. Catastrophic forgetting and mode collapse in gans. In International Joint Conference on Neural Networks. IEEE, 1\u201310."},{"issue":"11","key":"e_1_3_1_37_2","article-title":"Visualizing data using T-SNE.","volume":"9","author":"Maaten Laurens Van der","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using T-SNE. J. Mach. Learn. Res. 9, 11 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539253"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080786"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441800"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467289"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331201"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532058"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16578"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403218"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481952"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531937"},{"key":"e_1_3_1_51_2","article-title":"Self-supervised learning for recommender systems: A survey","author":"Yu Junliang","year":"2023","unstructured":"Junliang Yu, Hongzhi Yin, Xin Xia, Tong Chen, Jundong Li, and Zi Huang. 2023. Self-supervised learning for recommender systems: A survey. IEEE Trans. Knowl. Data Eng. (2023).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627159"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484126"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482016"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608811"},{"key":"e_1_3_1_56_2","first-page":"2256","volume-title":"Proceedings of the ACM Web Conference","author":"Zheng Yu","year":"2022","unstructured":"Yu Zheng, Chen Gao, Jianxin Chang, Yanan Niu, Yang Song, Depeng Jin, and Yong Li. 2022. Disentangling long and short-term interests for recommendation. In Proceedings of the ACM Web Conference. 2256\u20132267."},{"key":"e_1_3_1_57_2","first-page":"277","volume-title":"Proceedings of the ACM Web Conference","author":"Zhu Qiannan","year":"2022","unstructured":"Qiannan Zhu, Haobo Zhang, Qing He, and Zhicheng Dou. 2022. A gain-tuning dynamic negative sampler for recommendation. In Proceedings of the ACM Web Conference. 277\u2013285."},{"key":"e_1_3_1_58_2","first-page":"193","volume-title":"Proceedings of the ACM Web Conference","author":"Zhuo Jianhuan","year":"2022","unstructured":"Jianhuan Zhuo, Qiannan Zhu, Yinliang Yue, and Yuhong Zhao. 2022. Learning explicit user interest boundary for recommendation. In Proceedings of the ACM Web Conference. 193\u2013202."}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690656","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:06Z","timestamp":1750294686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690656"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,10]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3690656"],"URL":"https:\/\/doi.org\/10.1145\/3690656","relation":{},"ISSN":["2770-6699"],"issn-type":[{"value":"2770-6699","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,10]]},"assertion":[{"value":"2024-02-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}