Heterophily‐Aware Motif‐Guided Contrastive Learning for Robust Social Recommendation

Abstract

ABSTRACT The homophily principle serves as the core foundation of graph neural network (GNN) based social recommendation, which assumes socially connected users share similar preferences and enables neighbourhood aggregation for user representation learning. Most existing methods directly aggregate information from original social graphs, but this strategy is severely suboptimal due to the prevalent low preference‐aware homophily in real‐world social networks. We further reveal that nonpreference‐driven social connections introduce massive noise into GNN aggregation, leading to representation degradation, over‐smoothing and even performance decline. Existing efforts mostly focus on individual subproblems of social denoising, high‐order modelling or representation enhancement and fail to provide a systematic solution for these cascading challenges. In this paper, we propose H2Rec, a heterophily‐aware motif‐guided contrastive learning framework for low‐homophily social recommendation. It integrates a dual‐branch social aggregation module, a homophily‐enhanced contrastive alignment objective and a user‐adaptive fusion mechanism to suppress noise and learn robust user representations end‐to‐end. Extensive experiments on real‐world benchmarks show that H2Rec significantly outperforms state‐of‐the‐art methods on mainstream evaluation metrics.