Towards Communication Efficient and Fair Federated Personalized Sequential Recommendation

TL;DR

This paper introduces CF-FedSR, a federated recommendation system that enhances communication efficiency, fairness, and personalization, addressing key challenges in privacy-preserving sequential recommendation models.

Contribution

The paper proposes a novel federated recommendation algorithm that improves communication efficiency, fairness, and personalization through adaptive client selection, fairness-aware aggregation, and local fine-tuning.

Findings

CF-FedSR accelerates training with adaptive client selection.

The method improves fairness among heterogeneous clients.

Experimental results demonstrate enhanced recommendation performance.

Abstract

Federated recommendations leverage the federated learning (FL) techniques to make privacy-preserving recommendations. Though recent success in the federated recommender system, several vital challenges remain to be addressed: (i) The majority of federated recommendation models only consider the model performance and the privacy-preserving ability, while ignoring the optimization of the communication process; (ii) Most of the federated recommenders are designed for heterogeneous systems, causing unfairness problems during the federation process; (iii) The personalization techniques have been less explored in many federated recommender systems. In this paper, we propose a Communication efficient and Fair personalized Federated personalized Sequential Recommendation algorithm (CF-FedSR) to tackle these challenges. CF-FedSR introduces a communication-efficient scheme that employs adaptive client selection and clustering-based sampling to accelerate the training process. A fairness-aware model aggregation algorithm that can adaptively capture the data and performance imbalance among different clients to address the unfairness problems is proposed. The personalization module assists clients in making personalized recommendations and boosts the recommendation performance via local fine-tuning and model adaption. Extensive experimental results show the effectiveness and efficiency of our proposed method.