Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat

Erdong Hu, Yuxin Tang, Anastasios Kyrillidis, Chris Jermaine; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 19385-19396

We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether learning over data sets that do not have diverse sets of images affects the results; whether to use a pre-trained feature extraction "backbone"; how to evaluate learner performance (we argue that classification accuracy is not enough), among others. Overall, across a wide variety of settings, we find that vertically decomposing a neural network seems to give the best results, and outperforms more standard reconciliation-used methods.