Saved in:
Bibliographic Details
Main Authors: Jain, Shreyansh, Jerripothula, Koteswar Rao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.12903
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908454421004288
author Jain, Shreyansh
Jerripothula, Koteswar Rao
author_facet Jain, Shreyansh
Jerripothula, Koteswar Rao
contents Federated Learning is a collaborative machine learning paradigm that enables multiple clients to learn a global model without exposing their data to each other. Consequently, it provides a secure learning platform with privacy-preserving capabilities. This paper introduces a new dataset containing 23,326 images collected from eight different commercial sources and classified into 31 categories, similar to the Office-31 dataset. To the best of our knowledge, this is the first image classification dataset specifically designed for Federated Learning. We also propose two new Federated Learning algorithms, namely Fed-Cyclic and Fed-Star. In Fed-Cyclic, a client receives weights from its previous client, updates them through local training, and passes them to the next client, thus forming a cyclic topology. In Fed-Star, a client receives weights from all other clients, updates its local weights through pre-aggregation (to address statistical heterogeneity) and local training, and sends its updated local weights to all other clients, thus forming a star-like topology. Our experiments reveal that both algorithms perform better than existing baselines on our newly introduced dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12903
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Federated Learning for Commercial Image Sources
Jain, Shreyansh
Jerripothula, Koteswar Rao
Computer Vision and Pattern Recognition
Image and Video Processing
Federated Learning is a collaborative machine learning paradigm that enables multiple clients to learn a global model without exposing their data to each other. Consequently, it provides a secure learning platform with privacy-preserving capabilities. This paper introduces a new dataset containing 23,326 images collected from eight different commercial sources and classified into 31 categories, similar to the Office-31 dataset. To the best of our knowledge, this is the first image classification dataset specifically designed for Federated Learning. We also propose two new Federated Learning algorithms, namely Fed-Cyclic and Fed-Star. In Fed-Cyclic, a client receives weights from its previous client, updates them through local training, and passes them to the next client, thus forming a cyclic topology. In Fed-Star, a client receives weights from all other clients, updates its local weights through pre-aggregation (to address statistical heterogeneity) and local training, and sends its updated local weights to all other clients, thus forming a star-like topology. Our experiments reveal that both algorithms perform better than existing baselines on our newly introduced dataset.
title Federated Learning for Commercial Image Sources
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2507.12903