GPFedRec: Graph-guided Personalization for Federated Recommendation

TL;DR

GPFedRec introduces a privacy-preserving federated recommendation approach that constructs user-relation graphs from personalized embeddings without accessing user interaction data, enhancing recommendation accuracy.

Contribution

It proposes a novel graph-guided personalization method that constructs user-relation graphs from local embeddings, improving federated recommendation performance while preserving user privacy.

Findings

Outperforms existing federated recommendation methods on benchmark datasets

Enhances recommendation accuracy by leveraging user-relation graphs

Maintains data locality-based privacy protection

Abstract

The federated recommendation system is an emerging AI service architecture that provides recommendation services in a privacy-preserving manner. Using user-relation graphs to enhance federated recommendations is a promising topic. However, it is still an open challenge to construct the user-relation graph while preserving data locality-based privacy protection in federated settings. Inspired by a simple motivation, similar users share a similar vision (embeddings) to the same item set, this paper proposes a novel Graph-guided Personalization for Federated Recommendation (GPFedRec). The proposed method constructs a user-relation graph from user-specific personalized item embeddings at the server without accessing the users' interaction records. The personalized item embedding is locally fine-tuned on each device, and then a user-relation graph will be constructed by measuring the similarity among client-specific item embeddings. Without accessing users' historical interactions, we embody the data locality-based privacy protection of vanilla federated learning. Furthermore, a graph-guided aggregation mechanism is designed to leverage the user-relation graph and federated optimization framework simultaneously. Extensive experiments on five benchmark datasets demonstrate GPFedRec's superior performance. The in-depth study validates that GPFedRec can generally improve existing federated recommendation methods as a plugin while keeping user privacy safe. Code is available to ease reproducibility