Joint contrastive learning of structural and semantic for graph collaborative filtering

Abstract

Recently, graph collaborative filtering has been proposed as a superior recommendation technique, due to its outstanding capability of capturing high-order correlations from user–item interactions. Despite effectiveness, it still suffers from two limitations on representation learning: (1) imbalanced data distribution. User/item nodes with high-degree usually interfere with the representation learning process of low-degree nodes, deteriorating the recommendation accuracy; (2) structural noise vulnerability. The neighborhood aggregation scheme for the node representing could easily amplify structural noises, damaging the robustness of recommenders. The latest studies have made progress in overcoming the two limitations by capturing self-supervision signals via contrastive learning. Nevertheless, they somehow rely on heuristics to design, at a certain distance from a more comprehensive settlement.To make contrastive learning more entrenched with graph collaborative filtering, this paper proposes a multi-task framework JCG that integrates joint contrastive learning strategies with a backbone of graph-based recommender. Specifically, (1) we design six contrastive learning tasks categorized as structural and semantic, and obtain nine joint strategies by combining two tasks from each category; (2) we systematically study the effect of joint strategies on graph collaborative filtering, finding that JCG with feasible strategies could achieve up to 18.5% and 17.9% performance gain over the backbone on datasets of Yelp and ML, respectively; (3) performance comparison with other competitive baselines demonstrates the superiority of our JCG, especially that on mitigating the two limitations of data imbalance and noise vulnerability. We hope that our conclusion could provide new insight for future studies.