Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning

TL;DR

This paper introduces RGCL, a graph contrastive learning framework for recommendation systems that enhances robustness by dynamically balancing view hardness and invariance through decision boundary-aware adversarial techniques.

Contribution

The paper proposes a novel RGCL framework that maintains semantic invariance and adapts during training using decision boundary-aware perturbations and relation-aware view generation.

Findings

RGCL outperforms twelve baselines on five datasets.

The method improves robustness against data sparsity.

Theoretical analysis supports the effectiveness of the approach.

Abstract

In recent years, graph contrastive learning (GCL) has received increasing attention in recommender systems due to its effectiveness in reducing bias caused by data sparsity. However, most existing GCL models rely on heuristic approaches and usually assume entity independence when constructing contrastive views. We argue that these methods struggle to strike a balance between semantic invariance and view hardness across the dynamic training process, both of which are critical factors in graph contrastive learning. To address the above issues, we propose a novel GCL-based recommendation framework RGCL, which effectively maintains the semantic invariance of contrastive pairs and dynamically adapts as the model capability evolves through the training process. Specifically, RGCL first introduces decision boundary-aware adversarial perturbations to constrain the exploration space of contrastive augmented views, avoiding the decrease of task-specific information. Furthermore, to incorporate global user-user and item-item collaboration relationships for guiding on the generation of hard contrastive views, we propose an adversarial-contrastive learning objective to construct a relation-aware view-generator. Besides, considering that unsupervised GCL could potentially narrower margins between data points and the decision boundary, resulting in decreased model robustness, we introduce the adversarial examples based on maximum perturbations to achieve margin maximization. We also provide theoretical analyses on the effectiveness of our designs. Through extensive experiments on five public datasets, we demonstrate the superiority of RGCL compared against twelve baseline models.