Abstract
Collaborative filtering (CF) plays a crucial role in the development of recommendations. Most CF research focuses on implicit feedback due to its accessibility, but deriving user preferences from such feedback is challenging given the inherent noise in interactions. Existing works primarily employ unobserved interactions as negative samples, leading to a critical noisy-label problem. In this study, we propose SCLRec (Soft Contrastive Learning for Recommendations), a novel method to alleviate the noise issue in implicit recommendations. To this end, we first construct a similarity matrix based on user and item embeddings along with item popularity information. Subsequently, to leverage information from nearby samples, we employ entropy optimal transport to obtain the matching matrix from the similarity matrix. The matching matrix provides additional supervisory signals that uncover matching relationships of unobserved user-item interactions, thereby mitigating the noise issue. Finally, we treat the matching matrix as soft targets, and use them to train the model via contrastive learning loss. Thus, we term it soft contrastive learning, which combines the denoising capability of soft targets with the representational strength of contrastive learning to enhance implicit recommendations. Extensive experiments on three public datasets demonstrate that SCLRec achieves consistent performance improvements compared to state-of-the-art CF methods.
References
Cao, J., Cong, X., Sheng, J., Liu, T., Wang, B.: Contrastive cross-domain sequential recommendation. In: CIKM, pp. 138ā147 (2022)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597ā1607 (2020)
Cheng, M., et al.: Learning recommender systems with implicit feedback via soft target enhancement. In: SIGIR, pp. 575ā584 (2021)
Cheng, R., Wu, B., Zhang, P., Vajda, P., Gonzalez, J.E.: Data-efficient language-supervised zero-shot learning with self-distillation. In: CVPR, pp. 3119ā3124 (2021)
Cho, E., Myers, S.A., Leskovec, J.: Friendship and mobility: user movement in location-based social networks. In: KDD, pp. 1082ā1090 (2011)
Covington, P., Adams, J., Sargin, E.: Deep neural networks for youtube recommendations. In: RecSys, pp. 191ā198 (2016)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: NIPS, pp. 2292ā2300 (2013)
Damodaran, B.B., Flamary, R., Seguy, V., Courty, N.: An entropic optimal transport loss for learning deep neural networks under label noise in remote sensing images. Comput. Vis. Image Understand. 191(C), 1ā12 (2020)
Gao, T., Yao, X., Chen, D.: SimCSE: Simple contrastive learning of sentence embeddings. In: EMNLP, pp. 6894ā6910 (2021)
Gao, Y., et al.: Self-guided learning to denoise for robust recommendation. In: SIGIR, pp. 1412ā1422 (2022)
Harper, F.M., Konstan, J.A.: The movielens datasets: history and context. ACM Trans. Interact. Intell. Syst. 5(4), 1ā19 (2015)
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: Lightgcn: simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639ā648 (2020)
He, X., Zhang, H., Kan, M.Y., Chua, T.S.: Fast matrix factorization for online recommendation with implicit feedback. In: SIGIR, pp. 549ā558 (2016)
Jiang, Y., Huang, C., Huang, L.: Adaptive graph contrastive learning for recommendation. In: KDD, pp. 4252ā4261 (2023)
Lee, D., Kang, S., Ju, H., Park, C., Yu, H.: Bootstrapping user and item representations for one-class collaborative filtering. In: SIGIR, pp. 317ā326 (2021)
McAuley, J., Targett, C., Shi, Q., vanĀ den Hengel, A.: Image-based recommendations on styles and substitutes. In: SIGIR, pp. 43ā52 (2015)
Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Pan, R., et al.: One-class collaborative filtering. In: ICDM, pp. 502ā511 (2008)
Qiu, Z.H., Hu, Q., Yuan, Z., Zhou, D., Zhang, L., Yang, T.: Not all semantics are created equal: contrastive self-supervised learning with automatic temperature individualization. In: ICML, pp. 28389ā28421 (2023)
Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: bayesian personalized ranking from implicit feedback. In: UAI, pp. 452ā461 (2009)
Sankar, A., Wang, J., Krishnan, A., Sundaram, H.: Beyond localized graph neural networks: an attributed motif regularization framework. In: ICDM, pp. 472ā481 (2020)
Su, X., Khoshgoftaar, T.M.: A survey of collaborative filtering techniques. In: Advances in Artificial Intelligence, pp. 1ā19 (2009)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NIPS, pp. 1195ā1204 (2017)
Tian, C., Xie, Y., Li, Y., Yang, N., Zhao, W.X.: Learning to denoise unreliable interactions for graph collaborative filtering. In: SIGIR, pp. 122ā132 (2022)
Tianchi: IJCAI-16 brick-and-mortar store recommendation dataset (2018). https://tianchi.aliyun.com/dataset/dataDetail?dataId=53
Wang, C., et al.: Towards representation alignment and uniformity in collaborative filtering. In: KDD, pp. 1816ā1825 (2022)
Wang, W., Feng, F., He, X., Nie, L., Chua, T.S.: Denoising implicit feedback for recommendation. In: WSDM, pp. 373ā381 (2021)
Wang, Z., Xu, Q., Yang, Z., Cao, X., Huang, Q.: Implicit feedbacks are not always favorable: iterative relabeled one-class collaborative filtering against noisy interactions. In: MM, pp. 3070ā3078 (2021)
Wu, J., et al.: Self-supervised graph learning for recommendation. In: SIGIR, pp. 726ā735 (2021)
Yu, W., Qin, Z.: Sampler design for implicit feedback data by noisy-label robust learning. In: SIGIR, pp. 861ā870 (2020)
Zhou, C., Ma, J., Zhang, J., Zhou, J., Yang, H.: Contrastive learning for debiased candidate generation in large-scale recommender systems. In: KDD, pp. 3985ā3995 (2021)
Acknowledgements
This work was partially supported by NSFC (62122037) and the Collaborative Innovation Center of Novel Software Technology and Industrialization. We thank Zi-Hao Qiu for the helpful discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhuang, ZH., Zhang, L. (2024). Soft Contrastive Learning forĀ Implicit Feedback Recommendations. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14649. Springer, Singapore. https://doi.org/10.1007/978-981-97-2262-4_18
Download citation
DOI: https://doi.org/10.1007/978-981-97-2262-4_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2264-8
Online ISBN: 978-981-97-2262-4
eBook Packages: Computer ScienceComputer Science (R0)