Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation

TL;DR

This paper introduces a novel hyper meta-path contrastive learning framework that explicitly models complex user behavior dependencies for improved multi-behavior recommendation accuracy.

Contribution

It proposes the concept of hyper meta-paths to explicitly represent user behavior dependencies and leverages graph contrastive learning to adaptively learn unified user embeddings.

Findings

HMG-CR outperforms all baseline methods in experiments.

Explicit modeling of behavior dependencies improves recommendation performance.

Adaptive embedding learning captures complex user behavior patterns effectively.

Abstract

User purchasing prediction with multi-behavior information remains a challenging problem for current recommendation systems. Various methods have been proposed to address it via leveraging the advantages of graph neural networks (GNNs) or multi-task learning. However, most existing works do not take the complex dependencies among different behaviors of users into consideration. They utilize simple and fixed schemes, like neighborhood information aggregation or mathematical calculation of vectors, to fuse the embeddings of different user behaviors to obtain a unified embedding to represent a user's behavioral patterns which will be used in downstream recommendation tasks. To tackle the challenge, in this paper, we first propose the concept of hyper meta-path to construct hyper meta-paths or hyper meta-graphs to explicitly illustrate the dependencies among different behaviors of a user. How to obtain a unified embedding for a user from hyper meta-paths and avoid the previously mentioned limitations simultaneously is critical. Thanks to the recent success of graph contrastive learning, we leverage it to learn embeddings of user behavior patterns adaptively instead of assigning a fixed scheme to understand the dependencies among different behaviors. A new graph contrastive learning based framework is proposed by coupling with hyper meta-paths, namely HMG-CR, which consistently and significantly outperforms all baselines in extensive comparison experiments.