README.md

Research with NVIDIA FLARE

NVIDIA FLARE has been used in several research studies. In this directory, you can find their reference implementations.

Research Implementations

1. FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models ICML 2024
2. ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated Data (DeCaF 2023)
3. Fair Federated Medical Image Segmentation via Client Contribution Estimation (CVPR 2023)
4. Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples ICCV 2023
5. Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation (CVPR 2022)
6. Do Gradient Inversion Attacks Make Federated Learning Unsafe? (IEEE Transactions on Medical Imaging 2022)
7. Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation (ECCV 2022)
8. FedBN: Federated Learning on Non-IID Features via Local Batch Normalization ICLR 2021

Contributing

To provide your own research implementations, please follow this contribution guide.