Towards Federated Learning Across Biobanks: Prototype Software from the 2026 Carnegie Mellon University–NVIDIA Hackathon
https://doi.org/10.37044/osf.io/5psfj_v1
James Mu
, Aditya Kumar Karna
, Telaprolu Kumar Koushik
, Jeff Winchell
, Tyler Jay Yang
, Caiwei Maggie Zhang
, Jasmine Baker
, Espen Hagen
, Enamul Hoq
, Kyulin Kim
, Konstantinos Koukoutegos
, Peter Lawson
, Chantera Lazard
, Qianqian Liang
, Robert Loughnan
, Diya Patidar
, Chunduru Sri Abhijit
, Vibha Acharya
, Rahaf M. Ahmad
, Anna Boeva
, Jingyao Chen
, Ioannis Christofilogiannis
, Mariona Jaramillo Civill
, Heena Dalal
, Alina Devkota
, Amrit Gaire
, Dhruv Gor
, Aryan Sharan Guda
, Prashnna Gyawali
, Seungjin Han
, Jiahao He
, Yuan-Ting Hsieh
, Mengying Hu
, Peiran Jiang
, Pu Kao
, Adam Kehl
, Arnav Kharbanda
, Yajushi Khurana
, KUSHAL KOIRALA
, Sumeet Kothare
, Jędrzej Kubica
, Seohyun Lee
, Zilinghan Li
, Yosen Lin
, William Lu
, Jialan Ma
, Samarpan Mohanty
, Abraham G. Moller
, Derek Mu
, Shreyan Balaji Nalwad
, Shreya Nandakumar
, Hieu Ngo
, Bhanvi Paliwal
, Isha Parikh
, Zillur Rahman
, Arunannamalai Sujatha Bharath Raj
, Nikita Rajesh
, Shivank Sadasivan
, Ushta Samal
, Srikant Sarangi
, Andrew Scouten
, Aastha Shah
, Sanjnaa Sridhar
, Suratha Sriram
, Mrunali Abhijit Thokadiwala
, Jacob Thrasher
, Jeffrey Wang
, Yiman Wu
, Zhenghao Xiao
, Qiyu Yang
, Zhaoyi You
, Jiayi Zhao
, Jiayan Zhou
, Zheqian Zhu
, Pravesh Parekh
, Huajin Wang
, Melanie Gainey
, Sean Davis
, Beryl Rabindran
, Holger R. Roth
and Ben Busby
CMU26
The Carnegie Mellon University-NVIDIA Federated Learning Hackathon for Biomedical Applications (January 7-9, 2026) convened researchers from academia, government, and industry to implement federated frameworks for disease subtyping, genetic association studies, and multimodal clinical prediction using NVIDIA FLARE. This preprint presents ten projects spanninggenome-wide association analyses, histopathology harmonization, pangenome construction, ancestry deconvolution, rare disease stratification, cancer subtyping, polygenic risk score aggregation, and multimodal fusion. These proofs of principle collectively demonstrate both the versatility of federated learning for biomedical applications and the technical considerations required for successful deployment.