Multi-view Multi-behavior Contrastive Learning in Recommendation

TL;DR

This paper introduces MMCLR, a novel contrastive learning framework for multi-behavior recommendation that models commonalities, differences, and multi-view representations to improve recommendation accuracy.

Contribution

The paper proposes three new contrastive learning tasks within MMCLR to effectively model multi-behavior data from coarse to fine granularity and across different views.

Findings

Achieves state-of-the-art performance on real-world datasets.

Demonstrates the effectiveness of multi-view and multi-behavior contrastive learning.

Validates the importance of modeling fine-grained behavior differences.

Abstract

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}