Joint Graph Estimation and Signal Restoration for Robust Federated Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fukuhara, Tsutahiro, Hara, Junya, Higashi, Hiroshi, Tanaka, Yuichi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913844143587328
author Fukuhara, Tsutahiro
Hara, Junya
Higashi, Hiroshi
Tanaka, Yuichi
author_facet Fukuhara, Tsutahiro
Hara, Junya
Higashi, Hiroshi
Tanaka, Yuichi
contents We propose a robust aggregation method for model parameters in federated learning (FL) under noisy communications. FL is a distributed machine learning paradigm in which a central server aggregates local model parameters from multiple clients. These parameters are often noisy and/or have missing values during data collection, training, and communication between the clients and server. This may cause a considerable drop in model accuracy. To address this issue, we learn a graph that represents pairwise relationships between model parameters of the clients during aggregation. We realize it with a joint problem of graph learning and signal (i.e., model parameters) restoration. The problem is formulated as a difference-of-convex (DC) optimization, which is efficiently solved via a proximal DC algorithm. Experimental results on MNIST and CIFAR-10 datasets show that the proposed method outperforms existing approaches by up to $2$--$5\%$ in classification accuracy under biased data distributions and noisy conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11648
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint Graph Estimation and Signal Restoration for Robust Federated Learning
Fukuhara, Tsutahiro
Hara, Junya
Higashi, Hiroshi
Tanaka, Yuichi
Machine Learning
Signal Processing
We propose a robust aggregation method for model parameters in federated learning (FL) under noisy communications. FL is a distributed machine learning paradigm in which a central server aggregates local model parameters from multiple clients. These parameters are often noisy and/or have missing values during data collection, training, and communication between the clients and server. This may cause a considerable drop in model accuracy. To address this issue, we learn a graph that represents pairwise relationships between model parameters of the clients during aggregation. We realize it with a joint problem of graph learning and signal (i.e., model parameters) restoration. The problem is formulated as a difference-of-convex (DC) optimization, which is efficiently solved via a proximal DC algorithm. Experimental results on MNIST and CIFAR-10 datasets show that the proposed method outperforms existing approaches by up to $2$--$5\%$ in classification accuracy under biased data distributions and noisy conditions.
title Joint Graph Estimation and Signal Restoration for Robust Federated Learning
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2505.11648