Federated Learning for Commercial Image Sources

TL;DR

This paper introduces a new federated learning dataset for image classification from commercial sources and proposes two novel algorithms, Fed-Cyclic and Fed-Star, which outperform existing methods on this dataset.

Contribution

The paper presents the first federated learning image classification dataset from commercial sources and introduces two innovative algorithms tailored for federated topologies.

Findings

Both algorithms outperform existing baselines.

Fed-Cyclic and Fed-Star improve model accuracy.

New dataset enables better evaluation of federated learning methods.

Abstract

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.