PathMNIST

PathMNIST is a dataset that contains images of handwritten digits derived from the MNIST dataset, used to evaluate the performance of federated learning under varying levels of client heterogeneity.

Papers using PathMNIST (4)

Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning2026Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings2026DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix2026Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE, Flower, and Owkin Substra2025