Kun Zhou
ABSTRACT
Recently, significant progress has been made in sequential recommendation with deep learning. Existing neural sequential recommendation models usually rely on the item prediction loss to learn model parameters or data representations. However, the model trained with this loss is prone to suffer from data sparsity problem. Since it overemphasizes the final performance, the association or fusion between context data and sequence data has not been well captured and utilized for sequential recommendation.
To tackle this problem, we propose the model S3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture. The main idea of our approach is to utilize the intrinsic data correlation to derive self-supervision signals and enhance the data representations via pre-training methods for improving sequential recommendation. For our task, we devise four auxiliary self-supervised objectives to learn the correlations among attribute, item, subsequence, and sequence by utilizing the mutual information maximization (MIM) principle. MIM provides a unified way to characterize the correlation between different types of data, which is particularly suitable in our scenario. Extensive experiments conducted on six real-world datasets demonstrate the superiority of our proposed method over existing state-of-the-art methods, especially when only limited training data is available. Besides, we extend our self-supervised learning method to other recommendation models, which also improve their performance.
Supplemental Material
- J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT 2019. 4171--4186.Google Scholar
- M. Gutmann and A. Hyvarinen. 2012. Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics. J. Mach. Learn. Res., Vol. 13 (2012), 307--361.Google ScholarDigital Library
- B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk. 2016a. Session-based Recommendations with Recurrent Neural Networks. In ICLR 2016.Google Scholar
- B. Hidasi, M. Quadrana, A. Karatzoglou, and D. Tikk. 2016b. Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations. In RecSys 2016. 241--248.Google Scholar
- R. D. Hjelm, A. Fedorov, S. Lavoie-Marchildon, K. Grewal, P. Bachman, A. Trischler, and Y. Bengio. 2019. Learning deep representations by mutual information estimation and maximization. In ICLR 2019.Google Scholar
- J. Huang, Z. Ren, W. X. Zhao, G. He, J.-R. Wen, and D. Dong. 2019. Taxonomy-Aware Multi-Hop Reasoning Networks for Sequential Recommendation. In WSDM 2019. 573--581.Google Scholar
- J. Huang, W. X. Zhao, H. Dou, J.-R. Wen, and E. Y. Chang. 2018. Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks. In SIGIR 2018. 505--514.Google Scholar
- W.-C. Kang and J. J. McAuley. 2018. Self-Attentive Sequential Recommendation. In ICDM 2018. 197--206.Google Scholar
- D. P. Kingma and J. Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015.Google Scholar
- L. Kong, C. de Masson d'Autume, L. Yu, W. Ling, Z. Dai, and D. Yogatama. 2020. A Mutual Information Maximization Perspective of Language Representation Learning. In ICLR 2020.Google Scholar
- R. Linsker. 1988. Self-Organization in a Perceptual Network. IEEE Computer, Vol. 21, 3 (1988), 105--117.Google ScholarDigital Library
- L. Logeswaran and H. Lee. 2018. An efficient framework for learning sentence representations. In ICLR 2018.Google Scholar
- C. Ma, P. Kang, and X. Liu. 2019. Hierarchical Gating Networks for Sequential Recommendation. In KDD 2019. 825--833.Google Scholar
- J. J. McAuley, C. Targett, Q. Shi, and A. van den Hengel. 2015. Image-Based Recommendations on Styles and Substitutes. In SIGIR 2015. 43--52.Google Scholar
- T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In NeurIPS 2013. 3111--3119.Google Scholar
- R. Pasricha and J. J. McAuley. 2018. Translation-based factorization machines for sequential recommendation. In RecSys 2018. 63--71.Google ScholarDigital Library
- M. Quadrana, A. Karatzoglou, B. Hidasi, and P. Cremonesi. 2017. Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks. In RecSys 2017. 130--137.Google Scholar
- Pengjie Ren, Zhumin Chen, Jing Li, Zhaochun Ren, Jun Ma, and Maarten de Rijke. 2019. RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-Based Recommendation. In AAAI 2019. 4806--4813.Google ScholarDigital Library
- R. Ren, Z. Liu, Y. Li, W. X. Zhao, H. Wang, B. Ding, and J.-R. Wen. 2020. Sequential Recommendation with Self-Attentive Multi-Adversarial Network. In SIGIR 2020. 89--98.Google Scholar
- S. Rendle. 2010. Factorization Machines. In ICDM 2010. 995--1000.Google Scholar
- S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme. 2010. Factorizing personalized Markov chains for next-basket recommendation. In WWW 2010. 811--820.Google Scholar
- W. Song, C. Shi, Z. Xiao, Z. Duan, Y. Xu, M. Zhang, and J. Tang. 2019. AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks. In CIKM 2019. 1161--1170.Google Scholar
- F. Sun, J. Liu, J. Wu, C. Pei, X. Lin, W. Ou, and P. Jiang. 2019. BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. In CIKM 2019. 1441--1450.Google Scholar
- J. Tang and K. Wang. 2018. Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding. In WSDM 2018. 565--573.Google ScholarDigital Library
- A. van den Oord, Y. Li, and O. Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. CoRR, Vol. abs/1807.03748 (2018). arxiv: 1807.03748Google Scholar
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. 2017. Attention is All you Need. In NeurIPS 2017. 5998--6008.Google Scholar
- Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, and Joemon M. Jose. 2020. Self-Supervised Reinforcement Learning for Recommender Systems. In SIGIR 2020. 931--940.Google Scholar
- Y.-T. Yeh and Y.-N. Chen. 2019. QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization. In EMNLP-IJCNLP 2019. 3368--3373.Google Scholar
- T. Zhang, P. Zhao, Y. Liu, V. S. Sheng, J. Xu, D. Wang, G. Liu, and X. Zhou. 2019. Feature-level Deeper Self-Attention Network for Sequential Recommendation. In IJCAI 2019. 4320--4326.Google Scholar
- Kun Zhou, Wayne Xin Zhao, Shuqing Bian, Yuanhang Zhou, Ji-Rong Wen, and Jingsong Yu. 2020. Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion. In KDD 2020.Google Scholar
Index Terms
- S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization
Recommendations
Time Interval Aware Collaborative Sequential Recommendation with Self-supervised Learning
Web and Big DataAbstractOver the last few years, sequential recommender systems have achieved a great success in different applications. In the literature, it is generally believed that items farther away from the recommendation time have a weaker impact on the ...
A Self-Correcting Sequential Recommender
WWW '23: Proceedings of the ACM Web Conference 2023Sequential recommendations aim to capture users’ preferences from their historical interactions so as to predict the next item that they will interact with. Sequential recommendation methods usually assume that all items in a user’s historical ...
Self-Supervised Graph Co-Training for Session-based Recommendation
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementSession-based recommendation targets next-item prediction by exploiting user behaviors within a short time period. Compared with other recommendation paradigms, session-based recommendation suffers more from the problem of data sparsity due to the very ...
Comments