# Efficient federated learning for distributed neuroimaging data

## TL;DR

This paper introduces a new federated learning method for neuroimaging data that reduces communication costs by using sparse models.

## Contribution

A decentralized sparse federated learning strategy is proposed to reduce communication overhead in distributed neuroimaging data analysis.

## Key findings

- The sparse federated learning approach lowers communication overheads during training.
- The method is effective when applied to the Adolescent Brain Cognitive Development (ABCD) dataset.
- The approach accommodates diverse resource capabilities across different sites.

## Abstract

Recent advancements in neuroimaging have led to greater data sharing among the scientific community. However, institutions frequently maintain control over their data, citing concerns related to research culture, privacy, and accountability. This creates a demand for innovative tools capable of analyzing amalgamated datasets without the need to transfer actual data between entities. To address this challenge, we propose a decentralized sparse federated learning (FL) strategy. This approach emphasizes local training of sparse models to facilitate efficient communication within such frameworks. By capitalizing on model sparsity and selectively sharing parameters between client sites during the training phase, our method significantly lowers communication overheads. This advantage becomes increasingly pronounced when dealing with larger models and accommodating the diverse resource capabilities of various sites. We demonstrate the effectiveness of our approach through the application to the Adolescent Brain Cognitive Development (ABCD) dataset.