mlsanityData to 14 Oct 2026

Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning

arXiv 2601.22669 ↗First posted 30 Jan 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) facilitates decentralized collaborative learning without transmitting raw data. However, reliance on fixed global rounds or validation data for hyperparameter tuning hinders practical deployment by incurring high computational costs and privacy risks. To address this, we propose a data-free early stopping framework that determines the optimal stopping point by monitoring the task vector's growth rate using only server-side parameters. The numerical results on skin lesion/blood cell/colon pathology classification demonstrate that our approach is comparable to the validation-based early stopping across various state-of-the-art FL methods. In particular, the proposed framework requires an average of 45/12/31 (skin lesion/blood cell/colon pathology) additional rounds to achieve over 12.3%/8.9%/3.9% higher performance than early stopping based on validation data. Moreover, the proposed framework requires only 9/8/14 additional rounds to screen bad configurations, which is less than 3% of the fixed-round budget. To the best of our knowledge, this is the first work to propose a data-free early stopping framework for FL methods. Our code is available at this open repository.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

30 of 45 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  6. 2022Editing Models with Task Arithmeticcited by 1,120
  7. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  8. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  9. 2020The Future of Digital Health with Federated Learningcited by 633
  10. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  11. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  12. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
18 more
  1. 2021Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharingcited by 58
  2. 2023FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracycited by 49
  3. 2023Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscapecited by 46
  4. 2025When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformerscited by 38
  5. 2022Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directionscited by 35
  6. 2023A comprehensive survey on deep active learning in medical image analysiscited by 35
  7. 2022Federated Learning for Healthcare Domain - Pipeline, Applications and Challengescited by 34
  8. 2024Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimizationcited by 28
  9. 2024From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcarecited by 16
  10. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  11. 2023FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategycited by 10
  12. 2022Service Delay Minimization for Federated Learning over Mobile Devicescited by 9
  13. 2025On Task Vectors and Gradientscited by 7
  14. 2022Fast-Convergent Federated Learning via Cyclic Aggregationcited by 6
  15. 2025Revisit the Stability of Vanilla Federated Learning Under Diverse Conditionscited by 4
  16. 2025Debunking Optimization Myths in Federated Learning for Medical Image Classificationcited by 3
  17. 2025A Fast and Flat Federated Learning Method via Weighted Momentum and Sharpness-Aware Minimizationcited by 3
  18. 2025When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stoppingcited by 1

Built on by

Not cited yet.