DeepAI AI Chat
Log In Sign Up

Addressing Heterogeneity in Federated Learning via Distributional Transformation

by   Haolin Yuan, et al.
Duke University
Johns Hopkins University Applied Physics Laboratory
Johns Hopkins University

Federated learning (FL) allows multiple clients to collaboratively train a deep learning model. One major challenge of FL is when data distribution is heterogeneous, i.e., differs from one client to another. Existing personalized FL algorithms are only applicable to narrow cases, e.g., one or two data classes per client, and therefore they do not satisfactorily address FL under varying levels of data heterogeneity. In this paper, we propose a novel framework, called DisTrans, to improve FL performance (i.e., model accuracy) via train and test-time distributional transformations along with a double-input-channel model structure. DisTrans works by optimizing distributional offsets and models for each FL client to shift their data distribution, and aggregates these offsets at the FL server to further improve performance in case of distributional heterogeneity. Our evaluation on multiple benchmark datasets shows that DisTrans outperforms state-of-the-art FL methods and data augmentation methods under various settings and different degrees of client distributional heterogeneity.


page 1

page 2

page 3

page 4


Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection

Federated learning (FL) is a distributed machine learning paradigm that ...

FedConceptEM: Robust Federated Learning Under Diverse Distribution Shifts

Federated Learning (FL) is a machine learning paradigm that protects pri...

Auxo: Heterogeneity-Mitigating Federated Learning via Scalable Client Clustering

Federated learning (FL) is an emerging machine learning (ML) paradigm th...

Reliability and Performance Assessment of Federated Learning on Clinical Benchmark Data

As deep learning have been applied in a clinical context, privacy concer...

FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning

One of the key challenges in federated learning (FL) is local data distr...

LINDT: Tackling Negative Federated Learning with Local Adaptation

Federated Learning (FL) is a promising distributed learning paradigm, wh...

Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning

In federated learning (FL), model performance typically suffers from cli...