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

Autor:	Hu, Erdong, Tang, Yuxin, Kyrillidis, Anastasios, Jermaine, Chris
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Information Theory Mathematics - Optimization and Control
Druh dokumentu:	Working Paper
Popis:	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. Comment: 16 pages, 7 figures, Accepted at ICCV2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2309.03237 Zobrazit plný text záznamu View this record from Arxiv