FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling

TL;DR

FedHCDR tackles privacy-preserving cross-domain recommendation under data heterogeneity by introducing hypergraph signal decoupling (HSD), which splits user/item representations into domain-exclusive and domain-shared components via high-pass and low-pass hypergraph filters. Coupled with a local-global bi-directional transfer and a hypergraph contrastive learning (HCL) module, FedHCDR enables private federation across domains while emphasizing domain-shared signal through aggregation and perturbation-based learning. Empirical results on three real-world FedCDR scenarios show that FedHCDR consistently outperforms both single-domain baselines and existing federated cross-domain methods, highlighting the effectiveness of decoupling heterogeneous signals and leveraging cross-domain relationships. The approach contributes a principled way to mitigate negative transfer due to domain-specific information and demonstrates practical privacy-preserving improvements for cross-domain personalization in federated settings.

Abstract

In recent years, Cross-Domain Recommendation (CDR) has drawn significant attention, which utilizes user data from multiple domains to enhance the recommendation performance. However, current CDR methods require sharing user data across domains, thereby violating the General Data Protection Regulation (GDPR). Consequently, numerous approaches have been proposed for Federated Cross-Domain Recommendation (FedCDR). Nevertheless, the data heterogeneity across different domains inevitably influences the overall performance of federated learning. In this study, we propose FedHCDR, a novel Federated Cross-Domain Recommendation framework with Hypergraph signal decoupling. Specifically, to address the data heterogeneity across domains, we introduce an approach called hypergraph signal decoupling (HSD) to decouple the user features into domain-exclusive and domain-shared features. The approach employs high-pass and low-pass hypergraph filters to decouple domain-exclusive and domain-shared user representations, which are trained by the local-global bi-directional transfer algorithm. In addition, a hypergraph contrastive learning (HCL) module is devised to enhance the learning of domain-shared user relationship information by perturbing the user hypergraph. Extensive experiments conducted on three real-world scenarios demonstrate that FedHCDR outperforms existing baselines significantly.

Figures (6)

• Figure 1: Data heterogeneity across domains in the FedCDR scenario.
• Figure 2: An overview of FedHCDR.
• Figure 3: Initialization of hypergraph filter.
• Figure 4: Local-Global Bi-Directional Transfer Algorithm
• Figure 5: The predictive results of representations in FKCB and SGHT scenario.