Towards Fairness in Provably Communication-Efficient Federated Recommender Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kaur, Kirandeep, Gujar, Sujit, Jain, Shweta
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916259623337984
author Kaur, Kirandeep
Gujar, Sujit
Jain, Shweta
author_facet Kaur, Kirandeep
Gujar, Sujit
Jain, Shweta
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15788
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Fairness in Provably Communication-Efficient Federated Recommender Systems
Kaur, Kirandeep
Gujar, Sujit
Jain, Shweta
Information Retrieval
Human-Computer Interaction
Machine Learning
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.
title Towards Fairness in Provably Communication-Efficient Federated Recommender Systems
topic Information Retrieval
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2405.15788