Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling

TL;DR

This paper introduces GNMR, a graph neural network framework that models multiple types of user behaviors and their interactions to improve recommendation accuracy, outperforming existing methods on real-world datasets.

Contribution

Proposes a novel graph neural network model that explicitly captures multi-behavior user-item interactions for enhanced recommendation performance.

Findings

GNMR outperforms state-of-the-art methods on real-world datasets.

Explicit modeling of multi-behavior interactions improves recommendation accuracy.

Graph-based message passing effectively captures heterogeneous user-item relations.

Abstract

Many previous studies aim to augment collaborative filtering with deep neural network techniques, so as to achieve better recommendation performance. However, most existing deep learning-based recommender systems are designed for modeling singular type of user-item interaction behavior, which can hardly distill the heterogeneous relations between user and item. In practical recommendation scenarios, there exist multityped user behaviors, such as browse and purchase. Due to the overlook of user's multi-behavioral patterns over different items, existing recommendation methods are insufficient to capture heterogeneous collaborative signals from user multi-behavior data. Inspired by the strength of graph neural networks for structured data modeling, this work proposes a Graph Neural Multi-Behavior Enhanced Recommendation (GNMR) framework which explicitly models the dependencies between different types of user-item interactions under a graph-based message passing architecture. GNMR devises a relation aggregation network to model interaction heterogeneity, and recursively performs embedding propagation between neighboring nodes over the user-item interaction graph. Experiments on real-world recommendation datasets show that our GNMR consistently outperforms state-of-the-art methods. The source code is available at https://github.com/akaxlh/GNMR.