# An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracy

arXiv: https://arxiv.org/abs/2503.20768 · HTML: https://mlsanity.com/paper/2503.20768/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 60 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning](https://mlsanity.com/paper/2402.06954/) (2024)
- [FairFed: Enabling Group Fairness in Federated Learning](https://mlsanity.com/paper/2110.00857/) (2021)
- [Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning](https://mlsanity.com/paper/2202.05318/) (2022)
- [Improving Fairness for Data Valuation in Horizontal Federated Learning](https://mlsanity.com/paper/2109.09046/) (2021)
- [Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challenges](https://mlsanity.com/paper/2102.01375/) (2021)
- [Efficient and Secure Federated Learning for Financial Applications](https://mlsanity.com/paper/2303.08355/) (2023)
- [FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models](https://mlsanity.com/paper/2304.13407/) (2023)
- [Poisoning Federated Recommender Systems with Fake Users](https://mlsanity.com/paper/2402.11637/) (2024)
- [Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training](https://mlsanity.com/paper/2401.03748/) (2024)
- [Communication-Efficient Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2206.05558/) (2022)
- [FedMood: Federated Learning on Mobile Health Data for Mood Detection](https://mlsanity.com/paper/2102.09342/) (2021)
- [ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy](https://mlsanity.com/paper/2308.12210/) (2023)
- [Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy](https://mlsanity.com/paper/2212.04371/) (2022)

## Abstract (arXiv)

Federated Learning (FL) enables distributed ML model training on private user data at the global scale. Despite the potential of FL demonstrated in many domains, an in-depth view of its impact on model accuracy remains unclear. In this paper, we investigate, systematically, how this learning paradigm can affect the accuracy of state-of-the-art ML models for a variety of ML tasks. We present an empirical study that involves various data types: text, image, audio, and video, and FL configuration knobs: data distribution, FL scale, client sampling, and local and global computations. Our experiments are conducted in a unified FL framework to achieve high fidelity, with substantial human efforts and resource investments. Based on the results, we perform a quantitative analysis of the impact of FL, and highlight challenging scenarios where applying FL degrades the accuracy of the model drastically and identify cases where the impact is negligible. The detailed and extensive findings can benefit practical deployments and future development of FL.