Generalizable Hyperparameter Optimization for Federated Learning on Non-IID Cancer Images
Preprint
Abstract
Deep learning for cancer histopathology training conflicts with privacy constraints in clinical settings. Federated Learning (FL) mitigates this by keeping data local; however, its performance depends on hyperparameter choices under non-independent and identically distributed (non-IID) client datasets. This paper examined whether hyperparameters optimized on one cancer imaging dataset generalized across non-IID federated scenarios. We considered binary histopathology tasks for ovarian and colorectal cancers. We perform centralized Bayesian hyperparameter optimization and transfer dataset-specific optima to the non-IID FL setup. The main contribution of this study is the introduction of a simple cross-dataset aggregation heuristic by combining configurations by averaging the learning rates and considering the modal optimizers and batch sizes. This combined configuration achieves a competitive classification performance.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Enhancing Diabetes Disease Prediction and Privacy Preservation via Federated Learning and PSO-WCO OptimizationStatistics, Optimization & Information Computing, 2025
- IoT-Driven Skin Cancer Detection: Active Learning and Hyperparameter Optimization for Enhanced AccuracyIEEE Journal of Biomedical and Health Informatics, 2025
- MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classificationDigital Health, 2025
- Bilevel Hyperparameter Optimization and Neural Architecture Search for Enhanced Breast Cancer Detection in Smart Hospitals Interconnected With Decentralized Federated Learning EnvironmentIEEE Access, 2024
- Colorectal Cancer: Epidemiology, Risk Factors, and PreventionCancers, 2024
- Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countriesCA: A Cancer Journal for Clinicians, 2024
- Federated learning for medical image analysis: A surveyPattern Recognition, 2024
- Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCANGut, 2022
- Comparing convolutional neural networks and preprocessing techniques for HEp-2 cell classification in immunofluorescence imagesComputers in Biology and Medicine, 2020
- Hyperopt: a Python library for model selection and hyperparameter optimizationComputational Science & Discovery, 2015