Contrastive Learning for Sequential Recommendation

• Published in: Data engineering pp. 1259 - 1273
• Main Authors: Xie, Xu, Sun, Fei, Liu, Zhaoyang, Wu, Shiwen, Gao, Jinyang, Zhang, Jiandong, Ding, Bolin, Cui, Bin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2022
• Subjects: Behavioral sciences; Computer vision; Conferences; Contrastive Learning; Data engineering; Data mining; Data models; Deep Learning; Multitasking; Recom-mender Systems
• ISSN: 2375-026X
• DOI: 10.1109/ICDE53745.2022.00099

Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical inter-actions. Despite their success, we argue that these approaches usually rely on the sequential prediction task to optimize the huge amounts of parameters. They usually suffer from the data sparsity problem, which makes it difficult for them to learn high-quality user representations. To tackle that, inspired by recent advances of contrastive learning techniques in the computer vision, we propose a novel multi-task framework called Contrastive Learning for Sequential Recommendation (CL4SRec). CL4SRec not only takes advantage of the traditional next item prediction task but also utilizes the contrastive learning framework to derive self-supervision signals from the original user behavior sequences. Therefore, it can extract more meaningful user patterns and further encode the user representations effectively. In addition, we propose three data augmentation approaches to construct self-supervision signals. Extensive experiments on four public datasets demonstrate that CL4SRec achieves state-of-the-art performance over existing baselines by inferring better user representations.