Low-pass Personalized Subgraph Federated Recommendation

TL;DR

This paper introduces LPSFed, a federated recommendation system that uses spectral graph filtering and bias correction to handle structural imbalance across client subgraphs, improving accuracy and robustness.

Contribution

The paper proposes a novel spectral filtering approach with low-pass graph Fourier transforms and a bias-aware margin to address subgraph imbalance in federated recommendation systems.

Findings

LPSFed outperforms existing methods on five real-world datasets.

It achieves higher recommendation accuracy and robustness.

Theoretical analysis supports the effectiveness of spectral filtering.

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.