MixRec: Heterogeneous Graph Collaborative Filtering

TL;DR

MixRec is a novel heterogeneous graph collaborative filtering model that effectively captures multi-behavior user interactions and latent intent factors, improving recommendation accuracy especially in sparse data scenarios.

Contribution

The paper introduces MixRec, a heterogeneous hypergraph-based model with intent disentanglement and a contrastive learning paradigm, advancing multi-behavior modeling in recommender systems.

Findings

Significantly outperforms state-of-the-art baselines on three public datasets.

Effectively captures multi-behavior interaction patterns and latent user intents.

Enhances robustness against data sparsity through self-supervised contrastive learning.

Abstract

For modern recommender systems, the use of low-dimensional latent representations to embed users and items based on their observed interactions has become commonplace. However, many existing recommendation models are primarily designed for coarse-grained and homogeneous interactions, which limits their effectiveness in two critical dimensions. Firstly, these models fail to leverage the relational dependencies that exist across different types of user behaviors, such as page views, collects, comments, and purchases. Secondly, they struggle to capture the fine-grained latent factors that drive user interaction patterns. To address these limitations, we present a heterogeneous graph collaborative filtering model MixRec that excels at disentangling users' multi-behavior interaction patterns and uncovering the latent intent factors behind each behavior. Our model achieves this by incorporating intent disentanglement and multi-behavior modeling, facilitated by a parameterized heterogeneous hypergraph architecture. Furthermore, we introduce a novel contrastive learning paradigm that adaptively explores the advantages of self-supervised data augmentation, thereby enhancing the model's resilience against data sparsity and expressiveness with relation heterogeneity. To validate the efficacy of MixRec, we conducted extensive experiments on three public datasets. The results clearly demonstrate its superior performance, significantly outperforming various state-of-the-art baselines. Our model is open-sourced and available at: https://github.com/HKUDS/MixRec.