Privacy-Preserving Peer-to-Peer Cross-Domain Collaborative Filtering via Intent-Adaptive Graph Reconstruction

Abstract

Cross-domain collaborative filtering effectively alleviates the data sparsity issue but raises serious privacy concerns. Federated learning has been integrated into cross-domain collaborative filtering to reduce these risks by securely exchanging embeddings or model parameters. However, the current federated paradigm often relies on the simple alignment of coarse-grained representations, while propagating information on a rigid local graph. Without fine-grained preference modeling, models easily suffer from representation collapse. The inherent sparsity of local graphs further limits their robustness. To address these issues, we propose P2P-IAGR, a privacy-preserving peer-to-peer cross-domain collaborative filtering framework based on intent-adaptive graph reconstruction. Specifically, our framework first disentangles user and item representations into fine-grained latent intent prototypes. We perturb these prototypes using Local Differential Privacy (LDP) and securely exchange them across domains. A contrastive learning strategy is then used for cross-domain alignment. Next, guided by the combined cross-domain intent prior, P2P-IAGR differentiably reconstructs an augmented graph view. We apply a dual-view structural contrastive learning objective to dynamically inject external collaborative signals into the sparse local topology. Extensive experiments on real-world datasets show that P2P-IAGR significantly outperforms state-of-the-art methods, achieving an average improvement of 5.85% in NDCG and 6.89% in HR.