# Accelerating Federated Learning in Heterogeneous Data and Computational Environments

arXiv: https://arxiv.org/abs/2008.11281 · HTML: https://mlsanity.com/paper/2008.11281/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Scaling Neuroscience Research using Federated Learning](https://mlsanity.com/paper/2102.08440/) (2021)
- [Towards Multi-Objective Statistically Fair Federated Learning](https://mlsanity.com/paper/2201.09917/) (2022)
- [Performance Weighting for Robust Federated Learning Against Corrupted Sources](https://mlsanity.com/paper/2205.01184/) (2022)
- [FedBC: Calibrating Global and Local Models via Federated Learning Beyond Consensus](https://mlsanity.com/paper/2206.10815/) (2022)
- [Federated Learning over Harmonized Data Silos](https://mlsanity.com/paper/2305.08985/) (2023)
- [Secure & Private Federated Neuroimaging](https://mlsanity.com/paper/2205.05249/) (2022)

## Abstract (arXiv)

There are situations where data relevant to a machine learning problem are distributed among multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons. For example, data present in users' cellphones, manufacturing data of companies in a given industrial sector, or medical records located at different hospitals. Moreover, participating sites often have different data distributions and computational capabilities. Federated Learning provides an approach to learn a joint model over all the available data in these environments. In this paper, we introduce a novel distributed validation weighting scheme (DVW), which evaluates the performance of a learner in the federation against a distributed validation set. Each learner reserves a small portion (e.g., 5%) of its local training examples as a validation dataset and allows other learners models to be evaluated against it. We empirically show that DVW results in better performance compared to established methods, such as FedAvg, both under synchronous and asynchronous communication protocols in data and computationally heterogeneous environments.