Research with NVIDIA FLARE

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

For agent-assisted Auto-FL experiments, see the Auto-FL NVFlare starter bundle, which provides an autoresearch-style control plane, CIFAR-10 simulation harness, and bounded mutation workflow for NVFlare-based federated learning research loops.

Research Implementations

1. Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE (arXiv 2026)
2. FedNCA - Equitable Federated Learning with NCA (MICCAI 2025)
3. FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models (ICML 2024)
4. ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated Data (DeCaF 2023)
5. FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning (IJCAI 2023)
6. Fair Federated Medical Image Segmentation via Client Contribution Estimation (CVPR 2023)
7. Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples (ICCV 2023)
8. Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation (CVPR 2022)
9. Do Gradient Inversion Attacks Make Federated Learning Unsafe? (IEEE Transactions on Medical Imaging 2022)
10. Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation (ECCV 2022)
11. FedBN: Federated Learning on Non-IID Features via Local Batch Normalization (ICLR 2021)
12. Privacy-preserving Federated Brain Tumour Segmentation (MLMI 2019)

Contributing

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