论文标题
在推荐中多视图多行为对比学习
Multi-view Multi-behavior Contrastive Learning in Recommendation
论文作者
论文摘要
多行为建议（MBR）旨在共同考虑多种行为，以改善目标行为的表现。我们认为MBR模型应：（1）建模用户不同行为之间的粗粒度共同点，（2）考虑多行为建模中的单个序列视图和全局图视图，以及（3）捕获用户多种行为之间的细粒度差异。在这项工作中，我们提出了一个新颖的多行为多视图对比学习建议（MMCLR）框架，其中包括三个新的CL任务来解决上述挑战。多行为CL的目的是使每个视图中同一用户的不同用户单行为表示相似。多视图CL试图在用户的序列视图和图形视图表示之间弥合差距。行为区别CL的重点是建模不同行为的细粒差异。在实验中，我们进行了广泛的评估和消融测试，以验证MMCLR和在两个现实世界数据集上的各种CL任务的有效性，从而在现有基准方面实现了SOTA性能。我们的代码将在\ url {https://github.com/wyqing20/mmclr}上提供。
Multi-behavior recommendation (MBR) aims to jointly consider multiple behaviors to improve the target behavior's performance. We argue that MBR models should: (1) model the coarse-grained commonalities between different behaviors of a user, (2) consider both individual sequence view and global graph view in multi-behavior modeling, and (3) capture the fine-grained differences between multiple behaviors of a user. In this work, we propose a novel Multi-behavior Multi-view Contrastive Learning Recommendation (MMCLR) framework, including three new CL tasks to solve the above challenges, respectively. The multi-behavior CL aims to make different user single-behavior representations of the same user in each view to be similar. The multi-view CL attempts to bridge the gap between a user's sequence-view and graph-view representations. The behavior distinction CL focuses on modeling fine-grained differences of different behaviors. In experiments, we conduct extensive evaluations and ablation tests to verify the effectiveness of MMCLR and various CL tasks on two real-world datasets, achieving SOTA performance over existing baselines. Our code will be available on \url{https://github.com/wyqing20/MMCLR}
