# Robustness analytics to data heterogeneity in edge computing

arXiv: https://arxiv.org/abs/2002.05038 · HTML: https://mlsanity.com/paper/2002.05038/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Distributed Distributionally Robust Optimization with Non-Convex Objectives](https://mlsanity.com/paper/2210.07588/) (2022)
- [Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis](https://mlsanity.com/paper/2307.14364/) (2023)

## Abstract (arXiv)

Federated Learning is a framework that jointly trains a model textitwith complete knowledge on a remotely placed centralized server, but textitwithout the requirement of accessing the data stored in distributed machines. Some work assumes that the data generated from edge devices are identically and independently sampled from a common population distribution. However, such ideal sampling may not be realistic in many contexts. Also, models based on intrinsic agency, such as active sampling schemes, may lead to highly biased sampling. So an imminent question is how robust Federated Learning is to biased sampling? In this workfootnoteurlhttps://github.com/jiaqian/robustnessofFL, we experimentally investigate two such scenarios. First, we study a centralized classifier aggregated from a collection of local classifiers trained with data having categorical heterogeneity. Second, we study a classifier aggregated from a collection of local classifiers trained by data through active sampling at the edge. We present evidence in both scenarios that Federated Learning is robust to data heterogeneity when local training iterations and communication frequency are appropriately chosen.