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

Source: [Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat](<https://www.sota2.com/research/paper/68fa5ae01e209131ce9c3716>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:28:33.380Z

Authors: Erdong Hu, Yuxin Tang, Anastasios Kyrillidis, Chris Jermaine

Published: 2023-09-06T02:09:14.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.03237>)

[PDF](<https://arxiv.org/pdf/2309.03237.pdf>)