Federated Learning for Commercial Image Sources
This work addresses the need for privacy-preserving image classification in commercial applications, but it is incremental as it builds on existing federated learning paradigms with new algorithms and a dataset.
The paper tackled the problem of federated learning for image classification by introducing a new dataset of 23,326 images from commercial sources and proposing two algorithms, Fed-Cyclic and Fed-Star, which outperformed existing baselines on this dataset.
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.