mlsanityData to 7 Oct 2026

Revealing the influence of participant failures on model quality in cross-silo Federated Learning

arXiv 2603.25289 ↗First posted 26 Mar 2026cs.DC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a paradigm for training machine learning (ML) models in collaborative settings while preserving participants' privacy by keeping raw data local. A key requirement for the use of FL in production is reliability, as insufficient reliability can compromise the validity, stability, and reproducibility of learning outcomes. FL inherently operates as a distributed system and is therefore susceptible to crash failures, network partitioning, and other fault scenarios. Despite this, the impact of such failures on FL outcomes has not yet been studied systematically. In this paper, we address this gap by investigating the impact of missing participants in FL. To this end, we conduct extensive experiments on image, tabular, and time-series data and analyze how the absence of participants affects model performance, taking into account influencing factors such as data skewness, different availability patterns, and model architectures. Furthermore, we examine scenario-specific aspects, including the utility of the global model for missing participants. Our experiments provide detailed insights into the effects of various influencing factors. In particular, we show that data skewness has a strong impact, often leading to overly optimistic model evaluations and, in some cases, even altering the effects of other influencing factors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

20 of 31 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018Federated Learning with Non-IID Datacited by 1,099
  5. 2019Towards Federated Learning at Scale: System Designcited by 826
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  7. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  8. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 398
  9. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  10. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  11. 2020Towards Flexible Device Participation in Federated Learningcited by 64
  12. 2022Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraintscited by 30
8 more
  1. 2022Privacy-Preserving Aggregation in Federated Learning: A Surveycited by 25
  2. 2023FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropoutcited by 16
  3. 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updatescited by 13
  4. 2023MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updatescited by 10
  5. 2025FL-APU: A Software Architecture to Ease Practical Implementation of Cross-Silo Federated Learningcited by 3
  6. 2019Fog Computing as Privacy Enablercited by 2
  7. 2023Keep It Simple: Fault Tolerance Evaluation of Federated Learning with Unreliable Clientscited by 2
  8. 2025Analyzing the Impact of Participant Failures in Cross-Silo Federated Learningcited by 2

Built on by

Not cited yet.