Generalizable Hyperparameter Optimization for Federated Learning on Non-IID Cancer Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915737852968960 |
|---|---|
| author | Ribeiro, Elisa Gonçalves Moreira, Rodrigo Moreira, Larissa Ferreira Rodrigues Backes, André Ricardo |
| author_facet | Ribeiro, Elisa Gonçalves Moreira, Rodrigo Moreira, Larissa Ferreira Rodrigues Backes, André Ricardo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12664 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generalizable Hyperparameter Optimization for Federated Learning on Non-IID Cancer Images Ribeiro, Elisa Gonçalves Moreira, Rodrigo Moreira, Larissa Ferreira Rodrigues Backes, André Ricardo Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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. |
| title | Generalizable Hyperparameter Optimization for Federated Learning on Non-IID Cancer Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.12664 |