Fed-BioMed is an open source project focused on empowering biomedical research using non-centralized approaches for statistical analysis and machine learning. The project is currently based on Python, PyTorch and Scikit-learn, and enables developing and deploying federated learning analysis in real-world machine learning applications.
Start using Fed-BioMed, follow our tutorials and user guide.
What's federated learning?
Discover the advantages of federated learning with Fed-BioMed
The goal of Federated learning is to allow collaborative learning with decentralized data.
Healthcare is a typical application of federated learning: while hospitals across several geographical locations want to jointly train a machine learning model on the data hosted at each site, data cannot be shared between them because of privacy and security concerns. Federated learning gives us a methodological framework to train a global machine learning model, by only sharing the parameters of the models separately trained at each site. As a result, data never leaves the hospitals, and training is performed by simply aggregating models parameters to finally obtain a global model. Under certain conditions, the aggregated model faitfully represents the global variability across hospitals, and provides high generalization and robustness properties.
A new release of Fed-BioMed (v4.1) is out!
A new release of Fed-BioMed (v4.1) is out, introducing Scaffold aggregator, more integration testsRead More
Fed-BioMed for Federated-PET project
Federated-PET groups 8 hospitals and 4 research centers in an oncology research project.Read More
Users and Partners
Send a message to fedbiomed-support _at_ inria _dot_ fr or on the the Fed-BioMed support channel on Discord
and benefit from the feedback of the community.
When posting a support request, please pay attention to some tips:
- Be clear about what your problem is: what was the expected outcome,
what happened instead? Detail how someone else can recreate the problem.
- Additional infos: link to demos, screenshots or code showing the problem.
You may also want to subscribe to the support list.
If you want to be part of Fed-BioMed contact fedbiomed _at_ inria _dot_ fr