mlsanityData to 7 Oct 2026

Towards Fairness in Provably Communication-Efficient Federated Recommender Systems

arXiv 2405.15788 ↗First posted 3 May 2024cs.IR cs.HC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 68 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

30 of 68 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Neural Collaborative Filteringcited by 1,108
  3. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  4. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  5. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  6. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  7. 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
  8. 2020Optimal Client Sampling for Federated Learningcited by 123
  9. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
  10. 2021FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendationcited by 97
  11. 2017Beyond Parity: Fairness Objectives for Collaborative Filteringcited by 93
  12. 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
18 more
  1. 2021User-oriented Fairness in Recommendationcited by 75
  2. 2020Fairness-Aware Explainable Recommendation over Knowledge Graphscited by 74
  3. 2021On Large-Cohort Training for Federated Learningcited by 73
  4. 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
  5. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  6. 2020Neural Collaborative Reasoningcited by 37
  7. 2021Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Researchcited by 34
  8. 2022Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraintscited by 30
  9. 2022FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Servercited by 29
  10. 2022Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimizationcited by 23
  11. 2023No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendationcited by 18
  12. 2022Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneitycited by 17
  13. 2020DeepFair: Deep Learning for Improving Fairness in Recommender Systemscited by 12
  14. 2020Causal intersectionality for fair rankingcited by 12
  15. 2022Fair Federated Learning via Bounded Group Losscited by 12
  16. 2022Towards Communication Efficient and Fair Federated Personalized Sequential Recommendationcited by 7
  17. 2022Personalized Federated Learning with Server-Side Informationcited by 6
  18. 2022Cali3F: Calibrated Fast Fair Federated Recommendation Systemcited by 5

Built on by

Not cited yet.