When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, FL methods typically run for a predefined number of global rounds, often leading to unnecessary computation when optimal performance is reached earlier. In addition, training may continue even when the model fails to achieve meaningful performance. To address this inefficiency, we introduce a zero-shot synthetic validation framework that leverages generative AI to monitor model performance and determine early stopping points. Our approach adaptively stops training near the optimal round, thereby conserving computational resources and enabling rapid hyperparameter adjustments. Numerical results on multi-label chest X-ray classification demonstrate that our method reduces training rounds by up to 74% while maintaining accuracy within 1% of the optimal.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 19 references that are in the map. First posted on arXiv 14 Nov 2025.
Builds on
16 of 19 references.
References · 16
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2021Federated Learning Based on Dynamic Regularizationcited by 562
- 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
- 2017On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimizationcited by 92
- 2023FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracycited by 49
4 more
- 2023Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscapecited by 46
- 2023FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategycited by 10
- 2025Revisit the Stability of Vanilla Federated Learning Under Diverse Conditionscited by 4
- 2025Debunking Optimization Myths in Federated Learning for Medical Image Classificationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.