Pre-training Recommender Systems via Reinforced Attentive Multi-relational Graph Neural Network

TL;DR

This paper introduces RAM-GNN, a novel pre-training approach using reinforced attentive multi-relational GNNs to improve recommendation accuracy by effectively modeling complex, multi-relational graphs in recommender systems.

Contribution

The paper proposes RAM-GNN, a new method that pre-trains user and item embeddings on attribute-based sub-graphs with relation-level attention and reinforced neighbor sampling.

Findings

RAM-GNN outperforms state-of-the-art graph-based recommendation models.

The relation-level attention effectively captures relation importance.

Reinforced neighbor sampling improves neighbor selection and model performance.

Abstract

Recently, Graph Neural Networks (GNNs) have proven their effectiveness for recommender systems. Existing studies have applied GNNs to capture collaborative relations in the data. However, in real-world scenarios, the relations in a recommendation graph can be of various kinds. For example, two movies may be associated either by the same genre or by the same director/actor. If we use a single graph to elaborate all these relations, the graph can be too complex to process. To address this issue, we bring the idea of pre-training to process the complex graph step by step. Based on the idea of divide-and-conquer, we separate the large graph into three sub-graphs: user graph, item graph, and user-item interaction graph. Then the user and item embeddings are pre-trained from user and item graphs, respectively. To conduct pre-training, we construct the multi-relational user graph and item graph, respectively, based on their attributes. In this paper, we propose a novel Reinforced Attentive Multi-relational Graph Neural Network (RAM-GNN) to the pre-train user and item embeddings on the user and item graph prior to the recommendation step. Specifically, we design a relation-level attention layer to learn the importance of different relations. Next, a Reinforced Neighbor Sampler (RNS) is applied to search the optimal filtering threshold for sampling top-k similar neighbors in the graph, which avoids the over-smoothing issue. We initialize the recommendation model with the pre-trained user/item embeddings. Finally, an aggregation-based GNN model is utilized to learn from the collaborative relations in the user-item interaction graph and provide recommendations. Our experiments demonstrate that RAM-GNN outperforms other state-of-the-art graph-based recommendation models and multi-relational graph neural networks.