Dual-Channel Multiplex Graph Neural Networks for Recommendation

2024-03-18

arXiv.org

AI Summary

Existing recommender systems struggle to effectively model inter-behavior dependencies among heterogeneous user actions (e.g., click, favorite, purchase) and their differential impacts on the target behavior (e.g., purchase). To address this, we propose a dual-channel graph neural network framework: (1) an explicit behavioral pattern learner that captures co-occurrence patterns of multi-behavior interactions between users and items; and (2) a relation-chain-aware encoder that employs multi-hop neighborhood aggregation with gated attention to discover influence pathways and optimal relational sequences from auxiliary behaviors to the target behavior. This work is the first to jointly optimize behavioral pattern representation and relational chain structure. Extensive experiments on three real-world datasets demonstrate consistent improvements over state-of-the-art methods, achieving average gains of 10.06% in Recall@10 and 12.15% in NDCG@10.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our model surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10 respectively.

Problem

• Modeling user-item behavior patterns
• Capturing multiplex relations impact
• Enhancing recommendation accuracy

Innovation

• Dual-Channel Multiplex Graph Neural Network
• Explicit behavior pattern representation learner
• Relation chain-aware encoder