Task-Agnostic Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Zhengtao, Nguyen, Hong, Srivastava, Ajitesh, Ambite, Jose Luis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912177109073920
author Yao, Zhengtao
Nguyen, Hong
Srivastava, Ajitesh
Ambite, Jose Luis
author_facet Yao, Zhengtao
Nguyen, Hong
Srivastava, Ajitesh
Ambite, Jose Luis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17235
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Task-Agnostic Federated Learning
Yao, Zhengtao
Nguyen, Hong
Srivastava, Ajitesh
Ambite, Jose Luis
Computer Vision and Pattern Recognition
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
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.
title Task-Agnostic Federated Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2406.17235