Research map / Federated learning and privacy / Privacy attacks and secure learning
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
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 federated strategies instead of local-only training | FL strategies on Fed-KITS2019 and Fed-ISIC2019 · Fed-KITS2019, Fed-ISIC2019 | DICE / balanced accuracy | Helped |
| Use federated strategies instead of local-only training | FL strategies on Fed-Camelyon16, Fed-LIDC-IDRI, Fed-IXI · Fed-Camelyon16, Fed-LIDC-IDRI, Fed-IXI | AUC / DICE | No clear effect |
| Use federated strategies instead of pooled training | FL strategies on image datasets · Fed-Camelyon16, Fed-LIDC-IDRI, Fed-IXI, Fed-KITS2019, Fed-ISIC2019 | task metric | Hurt |
| Use federated strategies instead of pooled training | linear models on tabular data · Fed-TCGA-BRCA, Fed-Heart-Disease | C-index / accuracy | No clear effect |
| Use FedOpt variants (FedAdagrad, FedYogi, FedAdam) instead of FedAvg | FL strategies · datasets where FL beats pooled baseline | task metric | Helped |
| Use Cyclic learning instead of parallel strategies | Cyclic baseline · all FLamby datasets | task metric | Hurt |
| Use FedAvg compared with other strategies | FedAvg · Fed-Camelyon16, Fed-IXI | AUC / DICE | Helped |
| Use FL strategies on Fed-LIDC-IDRI | multiple FL strategies · Fed-LIDC-IDRI | DICE | Hurt |
| Add a balanced cross-entropy term (weight 0.1) to the DICE loss (ablation) | VNet loss · Fed-LIDC-IDRI | inference quality on non-nodule regions | Helped |
Closest papers by meaning
- dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis (CVPR 2025 · similarity 0.87)
- FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection (NeurIPS 2024 · similarity 0.87)
- FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning (CVPR 2024 · similarity 0.86)
- FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler (ICLR 2024 · similarity 0.86)
- PICSR: Prototype-Informed Cross-Silo Router for Federated Learning (Student Abstract) (AAAI 2024 · similarity 0.85)
- FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models (NeurIPS 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.