Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems

TL;DR

This paper introduces DPAO, a reinforcement learning framework with dual policies that adaptively optimize aggregation strategies in GNN-based recommender systems, significantly improving their performance across multiple datasets.

Contribution

It proposes a novel dual policy reinforcement learning framework for adaptive aggregation in GNN recommenders, addressing heterogeneity challenges and enhancing recommendation accuracy.

Findings

Significant improvements in nDCG and Recall metrics.

Effective adaptation of high-order connectivity aggregation.

Versatile performance across various GNN models and datasets.

Abstract

Graph Neural Networks (GNNs) provide powerful representations for recommendation tasks. GNN-based recommendation systems capture the complex high-order connectivity between users and items by aggregating information from distant neighbors and can improve the performance of recommender systems. Recently, Knowledge Graphs (KGs) have also been incorporated into the user-item interaction graph to provide more abundant contextual information; they are exploited to address cold-start problems and enable more explainable aggregation in GNN-based recommender systems (GNN-Rs). However, due to the heterogeneous nature of users and items, developing an effective aggregation strategy that works across multiple GNN-Rs, such as LightGCN and KGAT, remains a challenge. In this paper, we propose a novel reinforcement learning-based message passing framework for recommender systems, which we call DPAO (Dual Policy framework for Aggregation Optimization). This framework adaptively determines high-order connectivity to aggregate users and items using dual policy learning. Dual policy learning leverages two Deep-Q-Network models to exploit the user- and item-aware feedback from a GNN-R and boost the performance of the target GNN-R. Our proposed framework was evaluated with both non-KG-based and KG-based GNN-R models on six real-world datasets, and their results show that our proposed framework significantly enhances the recent base model, improving nDCG and Recall by up to 63.7% and 42.9%, respectively. Our implementation code is available at https://github.com/steve30572/DPAO/.