Towards Fairness in Provably Communication-Efficient Federated Recommender Systems

TL;DR

This paper introduces RS-FairFRS, a federated recommender system that improves communication efficiency and fairness by theoretical analysis, empirical validation, and a novel dual-fair update technique that reduces bias without exposing sensitive data.

Contribution

It provides the first sample complexity bounds for communication-efficient federated recommender systems and proposes a dual-fair update method to enhance fairness without revealing protected attributes.

Findings

RS-FairFRS reduces communication costs by approximately 47%.

The dual-fair update technique significantly decreases demographic bias (~40%).

Theoretical bounds guide optimal client sampling for accuracy and efficiency.

Abstract

To reduce the communication overhead caused by parallel training of multiple clients, various federated learning (FL) techniques use random client sampling. Nonetheless, ensuring the efficacy of random sampling and determining the optimal number of clients to sample in federated recommender systems (FRSs) remains challenging due to the isolated nature of each user as a separate client. This challenge is exacerbated in models where public and private features can be separated, and FL allows communication of only public features (item gradients). In this study, we establish sample complexity bounds that dictate the ideal number of clients required for improved communication efficiency and retained accuracy in such models. In line with our theoretical findings, we empirically demonstrate that RS-FairFRS reduces communication cost (~47%). Second, we demonstrate the presence of class imbalance among clients that raises a substantial equity concern for FRSs. Unlike centralized machine learning, clients in FRS can not share raw data, including sensitive attributes. For this, we introduce RS-FairFRS, first fairness under unawareness FRS built upon random sampling based FRS. While random sampling improves communication efficiency, we propose a novel two-phase dual-fair update technique to achieve fairness without revealing protected attributes of active clients participating in training. Our results on real-world datasets and different sensitive features illustrate a significant reduction in demographic bias (~approx40\%), offering a promising path to achieving fairness and communication efficiency in FRSs without compromising the overall accuracy of FRS.