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

• URL: http://arxiv.org/abs/2603.25289v1
• Date: Thu, 26 Mar 2026 10:28:40 GMT
• Title: Revealing the influence of participant failures on model quality in cross-silo Federated Learning
• Abstract summary: Federated Learning (FL) is a paradigm for training machine learning (ML) models in collaborative settings.<n>In this paper, we investigate the impact of missing participants on FL outcomes.<n>We take into account influencing factors such as data skewness, different availability patterns, and model architectures.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Analyzing the Impact of Participant Failures in Cross-Silo Federated Learning [0.0]
  Federated learning (FL) is a new paradigm for training machine learning (ML) models without sharing data.<n>We study the impact of participant failures on the model quality in the context of cross-silo FL with few participants.<n>Our results offer insights for researchers and software architects aiming to build robust FL systems.
  arXiv  Detail & Related papers  (2025-11-18T12:59:51Z)
• Data Fusion for Partial Identification of Causal Effects [62.56890808004615]
  We propose a novel partial identification framework that enables researchers to answer key questions.<n>Is the causal effect positive or negative? and How severe must assumption violations be to overturn this conclusion?<n>We apply our framework to the Project STAR study, which investigates the effect of classroom size on students' third-grade standardized test performance.
  arXiv  Detail & Related papers  (2025-05-30T07:13:01Z)
• An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracy [6.907897341928317]
  Federated Learning (FL) enables distributed ML model training on private user data at the global scale.<n>We investigate, systematically, how this learning paradigm can affect the accuracy of state-of-the-art ML models for a variety of ML tasks.
  arXiv  Detail & Related papers  (2025-03-26T17:52:30Z)
• A Thorough Assessment of the Non-IID Data Impact in Federated Learning [1.89791888476598]
  Decentralized machine learning (FL) allows collaborative machine learning (ML) training among decentralized clients' information, ensuring data privacy.<n>The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data.<n>Despite its importance, experimental studies systematically addressing all types of data heterogeneity (ak.a. non-IIDness) remain scarce.<n>We aim to fill this gap by assessing and quantifying the non-IID effect through a thorough empirical analysis.
  arXiv  Detail & Related papers  (2025-03-21T11:53:36Z)
• The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective [12.916988821333124]
  In federated learning (FL), model aggregation is a critical step by which multiple clients share their knowledge with one another.<n>This temporary performance drop can potentially slow down the convergence of the FL model.<n>We propose several simple yet effective strategies to mitigate the negative impacts of model aggregation.
  arXiv  Detail & Related papers  (2025-02-05T14:45:56Z)
• Feasible Learning [78.6167929413604]
  We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample.<n>Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
  arXiv  Detail & Related papers  (2025-01-24T20:39:38Z)
• Striving for data-model efficiency: Identifying data externalities on group performance [75.17591306911015]
  Building trustworthy, effective, and responsible machine learning systems hinges on understanding how differences in training data and modeling decisions interact to impact predictive performance. We focus on a particular type of data-model inefficiency, in which adding training data from some sources can actually lower performance evaluated on key sub-groups of the population. Our results indicate that data-efficiency is a key component of both accurate and trustworthy machine learning.
  arXiv  Detail & Related papers  (2022-11-11T16:48:27Z)
• Confounder Identification-free Causal Visual Feature Learning [84.28462256571822]
  We propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders. CICF models the interventions among different samples based on front-door criterion, and then approximates the global-scope intervening effect upon the instance-level interventions. We uncover the relation between CICF and the popular meta-learning strategy MAML, and provide an interpretation of why MAML works from the theoretical perspective.
  arXiv  Detail & Related papers  (2021-11-26T10:57:47Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)
• Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data [23.67491703843822]
  Federated learning (FL) is an emerging, privacy-preserving machine learning paradigm, drawing tremendous attention in academia and industry. A unique characteristic of FL is heterogeneity, which resides in the various hardware specifications and dynamic states across the participating devices. We conduct extensive experiments to compare the performance of state-of-the-art FL algorithms under Heterogeneous and Heterogeneous-unaware settings.
  arXiv  Detail & Related papers  (2020-06-12T07:49:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.