Low-pass Personalized Subgraph Federated Recommendation

ICLR 2026 Conference Submission15916 Authors

Keywords: Federated Learning, Recommender Systems, Graph Neural Networks

TL;DR: LPSFed addresses subgraph structural imbalance in federated recommendation via low-pass spectral filtering and a localized bias-aware loss, enabling robust personalized updates that enhance both accuracy and diversity across diverse client subgraphs.

Abstract:

Federated Recommender Systems (FRS) preserve privacy by training decentralized models on client-specific user-item subgraphs without sharing raw data. However, FRS faces a unique challenge: subgraph structural imbalance, where drastic variations in subgraph scale (user/item counts) and connectivity (item degree) misalign client representations, making it challenging to train a robust model that respects each client’s unique structural characteristics.

To address this, we propose a Low-pass Personalized Subgraph Federated recommender system (LPSFed). LPSFed leverages graph Fourier transforms and low-pass spectral filtering to extract low-frequency structural signals that remain stable across subgraphs of varying size and degree, allowing robust personalized parameter updates guided by similarity to a neutral structural anchor. Additionally, we leverage a localized popularity bias-aware margin that captures item-degree imbalance within each subgraph and incorporates it into a personalized bias correction term to mitigate recommendation bias. Supported by theoretical analysis and validated on five real-world datasets, LPSFed achieves superior recommendation accuracy and enhances model robustness.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 15916