mlsanityData to 7 Oct 2026

Loss Tolerant Federated Learning

arXiv 2105.03591 ↗First posted 8 May 2021cs.LG cs.AI cs.NIcited by 8

Not on the map. Why?

Abstract (arXiv)

Federated learning has attracted attention in recent years for collaboratively training data on distributed devices with privacy-preservation. The limited network capacity of mobile and IoT devices has been seen as one of the major challenges for cross-device federated learning. Recent solutions have been focusing on threshold-based client selection schemes to guarantee the communication efficiency. However, we find this approach can cause biased client selection and results in deteriorated performance. Moreover, we find that the challenge of network limit may be overstated in some cases and the packet loss is not always harmful. In this paper, we explore the loss tolerant federated learning (LT-FL) in terms of aggregation, fairness, and personalization. We use ThrowRightAway (TRA) to accelerate the data uploading for low-bandwidth-devices by intentionally ignoring some packet losses. The results suggest that, with proper integration, TRA and other algorithms can together guarantee the personalization and fairness performance in the face of packet loss below a certain fraction (10%-30%).

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 8 May 2021.

Builds on

16 of 30 references.

References · 16

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  3. 2019Towards Federated Learning at Scale: System Designcited by 826
  4. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  5. 2019Agnostic Federated Learningcited by 451
  6. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  7. 2019Fair Resource Allocation in Federated Learningcited by 389
  8. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  9. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  10. 2020Fairness in Machine Learningcited by 194
  11. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  12. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 162
4 more
  1. 2020Collaborative Fairness in Federated Learningcited by 95
  2. 2017Artificial Intelligence and Statisticscited by 43
  3. 2020CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learningcited by 6
  4. 2020Federated Learning with Communication Delay in Edge Networkscited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 2; 2025: 1.

8 papers.

  1. 2021Towards Fairness-Aware Federated Learningcited by 57
  2. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  3. 2022A Snapshot of the Frontiers of Client Selection in Federated Learningcited by 9
  4. 2023Entropy-driven Fair and Effective Federated Learningcited by 4
  5. 2024Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectivescited by 3
  6. 2025Fairness in Federated Learning: Trends, Challenges, and Opportunitiescited by 3
  7. 2023SplitFed resilience to packet loss: Where to split, that is the questioncited by 2
  8. 2024Optimizing Split Points for Error-Resilient SplitFed Learningcited by 1