Research map / Federated learning and privacy / Personalized and heterogeneous FL
HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use HarmoFL instead of FedBN | Federated breast histology classification · Breast Cancer Histology Image Classification | accuracy (%): 87.33 -> 95.48 | Helped |
| Use HarmoFL instead of FedBN | Federated nuclei segmentation · Histology Nuclei Segmentation | Dice (%): 70.27 -> 74.42 | Helped |
| Use HarmoFL instead of FedBN | Federated prostate MRI segmentation · Prostate MRI Segmentation | Dice (%): 92.75 -> 94.28 | Helped |
| Add amplitude normalization to FedAvg (ablation) | Federated breast histology classification · Breast Cancer Histology Image Classification | accuracy (%): 83.1 -> 92.6 | Helped |
| Add weight perturbation to FedAvg with AmpNorm (ablation) | Federated breast histology classification · Breast Cancer Histology Image Classification | accuracy (%): 92.6 -> 95.9 | Helped |
| Add amplitude normalization to FedAvg (ablation) | Federated nuclei segmentation · Histology Nuclei Segmentation | Dice (%): 67.6 -> 72.7 | Helped |
| Add weight perturbation to FedAvg with AmpNorm (ablation) | Federated nuclei segmentation · Histology Nuclei Segmentation | Dice (%): 72.7 -> 74.5 | Helped |
| Add amplitude normalization to FedAvg (ablation) | Federated prostate MRI segmentation · Prostate MRI Segmentation | Dice (%): 91.5 -> 93.2 | Helped |
| Add weight perturbation to FedAvg with AmpNorm (ablation) | Federated prostate MRI segmentation · Prostate MRI Segmentation | Dice (%): 93.2 -> 94.7 | Helped |
| Increase local training epochs (ablation) | HarmoFL and competing federated methods · Breast Cancer Histology Image Classification | testing accuracy | Mixed |
| Vary perturbation degree alpha from the selected value (ablation) | HarmoFL · Breast Cancer Histology Image Classification | testing accuracy | Mixed |
Closest papers by meaning
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.87)
- Dual-calibrated Co-training Framework for Personalized Federated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.86)
- Overcoming Heterogeneous Data in Federated Medical Vision-Language Pre-training: A Triple-Embedding Model Selector Approach (AAAI 2025 · similarity 0.86)
- FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models (CVPR 2025 · similarity 0.86)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.85)
- Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.