Secure Federated Graph-Filtering for Recommender Systems

TL;DR

This paper introduces two decentralized, privacy-preserving frameworks for computing graph filters in recommender systems, achieving comparable accuracy to centralized methods while enhancing data security and reducing communication costs.

Contribution

It proposes novel decentralized algorithms using Multi-Party Computation and low-rank approximations for secure graph filtering in recommender systems.

Findings

Achieves comparable accuracy to centralized methods.

Ensures data confidentiality and privacy.

Maintains low communication costs.

Abstract

Recommender systems often rely on graph-based filters, such as normalized item-item adjacency matrices and low-pass filters. While effective, the centralized computation of these components raises concerns about privacy, security, and the ethical use of user data. This work proposes two decentralized frameworks for securely computing these critical graph components without centralizing sensitive information. The first approach leverages lightweight Multi-Party Computation and distributed singular vector computations to privately compute key graph filters. The second extends this framework by incorporating low-rank approximations, enabling a trade-off between communication efficiency and predictive performance. Empirical evaluations on benchmark datasets demonstrate that the proposed methods achieve comparable accuracy to centralized state-of-the-art systems while ensuring data confidentiality and maintaining low communication costs. Our results highlight the potential for privacy-preserving decentralized architectures to bridge the gap between utility and user data protection in modern recommender systems.