datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
FL-MedClsBench
FL-MedClsBench
Beyond Synthetic Splits: A Benchmark for Federated Learning on Real-World Medical Data Classification
FL-MedClsBench is a comprehensive federated learning benchmark covering 10 multi-center medical datasets across diverse imaging modalities. Unlike existing benchmarks that rely on synthetic data partitioning, FL-MedClsBench uses naturally distributed multi-center clinical data to evaluate federated and personalized federated learning methods under realistic… See the full description on the dataset page: https://huggingface.co/datasets/FL-MedClsBench/FL-MedClsBench.FL-MedClsBench
FL-MedClsBench — Representative Sample
Beyond Synthetic Splits: A Benchmark for Federated Learning on Real-World Medical Data Classification
This is a representative sample of the full FL-MedClsBench dataset (>14 GB).
Sampling Methodology
Images: 5 samples randomly selected per client (seed=42)
FL-BCa (3D NIfTI MRI): 2 volumes per center
FL-ECG (HDF5 ECG signals): full dataset included (~7 GB, 3 files)
Metadata: All CSV split files (train/val/test × 3 seeds)… See the full description on the dataset page: https://huggingface.co/datasets/ccbi/FL-MedClsBench.FL-MedClsBench-sample
FL-MedClsBench — Representative Sample
Beyond Synthetic Splits: A Benchmark for Federated Learning on Real-World Medical Data Classification
This is a representative sample of the full FL-MedClsBench dataset (>14 GB).
Sampling Methodology
Images: 5 samples randomly selected per client (seed=42)
FL-BCa (3D NIfTI MRI): 2 volumes per center
FL-ECG (HDF5 ECG signals): full dataset included (~7 GB, 3 files)
Metadata: All CSV split files (train/val/test × 3 seeds) included in… See the full description on the dataset page: https://huggingface.co/datasets/FL-MedClsBench/FL-MedClsBench-sample.