# HeteroSwitch: Characterizing and Taming System-Induced Data Heterogeneity in Federated Learning

arXiv: https://arxiv.org/abs/2403.04207 · HTML: https://mlsanity.com/paper/2403.04207/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 61 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 30 of 33)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Three Approaches for Personalization with Applications to Federated Learning](https://mlsanity.com/paper/2002.10619/) (2020)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Papaya: Practical, Private, and Scalable Federated Learning](https://mlsanity.com/paper/2111.04877/) (2021)
- [A Deeper Look at Dataset Bias](https://mlsanity.com/paper/1505.01257/) (2015)
- [Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development](https://mlsanity.com/paper/2108.04308/) (2021)
- [Towards Fairness-Aware Federated Learning](https://mlsanity.com/paper/2111.01872/) (2021)
- [Batch Normalization Embeddings for Deep Domain Generalization](https://mlsanity.com/paper/2011.12672/) (2020)
- [Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework](https://mlsanity.com/paper/2010.15965/) (2020)
- [Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data](https://mlsanity.com/paper/2105.07066/) (2021)
- [AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning](https://mlsanity.com/paper/2107.08147/) (2021)
- [Reconfiguring the Imaging Pipeline for Computer Vision](https://mlsanity.com/paper/1705.04352/) (2017)
- [FLAIR: Federated Learning Annotated Image Repository](https://mlsanity.com/paper/2207.08869/) (2022)
- [Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity](https://mlsanity.com/paper/2206.02633/) (2022)
- [Neural Network Generalization: The impact of camera parameters](https://mlsanity.com/paper/1912.03604/) (2019)

## Built on by (most cited first, 1 of 1)

- [Federated Learning Clients Clustering with Adaptation to Data Drifts](https://mlsanity.com/paper/2411.01580/) (2024)

## Abstract (arXiv)

Federated Learning (FL) is a practical approach to train deep learning models collaboratively across user-end devices, protecting user privacy by retaining raw data on-device. In FL, participating user-end devices are highly fragmented in terms of hardware and software configurations. Such fragmentation introduces a new type of data heterogeneity in FL, namely textitsystem-induced data heterogeneity, as each device generates distinct data depending on its hardware and software configurations. In this paper, we first characterize the impact of system-induced data heterogeneity on FL model performance. We collect a dataset using heterogeneous devices with variations across vendors and performance tiers. By using this dataset, we demonstrate that textitsystem-induced data heterogeneity negatively impacts accuracy, and deteriorates fairness and domain generalization problems in FL. To address these challenges, we propose HeteroSwitch, which adaptively adopts generalization techniques (i.e., ISP transformation and SWAD) depending on the level of bias caused by varying HW and SW configurations. In our evaluation with a realistic FL dataset (FLAIR), HeteroSwitch reduces the variance of averaged precision by 6.3% across device types.