Successful Workshop on Federated Ensemble Learning at ISMB 2024

We are pleased to announce the successful completion of the workshop titled ‘Federated Ensemble Learning for Biomedical Data’, held during the prestigious ISMB 2024 conference in Montreal on July 12th. The workshop was organized by Anne-Christin Hauschild, Youngjun Park, Hryhorii Chereda, and Maryam Moradpour as part of the FAIrPaCT project.

The tutorial provided a deep dive into the theory and practice of federated learning and federated ensemble learning, focusing on the advantages of these techniques in biomedical data analysis. The workshop featured hands-on demonstrations of federated ensemble learning methods, including the implementation of Federated Random Forest and Ensemble-GNN using Python.

Participants worked with breast cancer data, incorporating both clinical and gene expression features, and learned how to apply these federated methods in a privacy-preserving setup. The tutorial was designed to equip participants with the theoretical understanding and practical skills necessary to deploy federated models in real-world biomedical applications.

The workshop received positive feedback from participants for its comprehensive coverage of topics and its ability to blend theory with practical insights. By the end of the session, attendees had gained valuable experience in privacy-preserving techniques for biomedical data analysis, furthering their understanding of how to securely handle sensitive data within a federated learning framework.

The success of this workshop highlights the growing importance of federated ensemble learning in biomedical research and demonstrates its potential to enhance data security while promoting collaborative scientific advancement.