Task-Agnostic Federated Learning

TL;DR

This paper proposes a task-agnostic federated learning framework using Vision Transformer and self-supervised pre-training to improve medical imaging models' generalization across diverse, privacy-sensitive datasets with minimal labeled data.

Contribution

It introduces a novel self-supervised federated learning approach that handles task heterogeneity and out-of-distribution generalization without requiring labels or task disclosure.

Findings

Retains 90% of centralized F1 accuracy with only 5% of training data

Demonstrates superior adaptability to unseen tasks and out-of-distribution data

Validates effectiveness on real-world non-IID medical imaging datasets

Abstract

In the realm of medical imaging, leveraging large-scale datasets from various institutions is crucial for developing precise deep learning models, yet privacy concerns frequently impede data sharing. federated learning (FL) emerges as a prominent solution for preserving privacy while facilitating collaborative learning. However, its application in real-world scenarios faces several obstacles, such as task & data heterogeneity, label scarcity, non-identically distributed (non-IID) data, computational vaiation, etc. In real-world, medical institutions may not want to disclose their tasks to FL server and generalization challenge of out-of-network institutions with un-seen task want to join the on-going federated system. This study address task-agnostic and generalization problem on un-seen tasks by adapting self-supervised FL framework. Utilizing Vision Transformer (ViT) as consensus feature encoder for self-supervised pre-training, no initial labels required, the framework enabling effective representation learning across diverse datasets and tasks. Our extensive evaluations, using various real-world non-IID medical imaging datasets, validate our approach's efficacy, retaining 90\% of F1 accuracy with only 5\% of the training data typically required for centralized approaches and exhibiting superior adaptability to out-of-distribution task. The result indicate that federated learning architecture can be a potential approach toward multi-task foundation modeling.