# FedHarmony: Unlearning Scanner Bias with Distributed Data

arXiv: https://arxiv.org/abs/2205.15970 · HTML: https://mlsanity.com/paper/2205.15970/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 31 May 2022.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation](https://mlsanity.com/paper/1810.04304/) (2018)
- [Federated Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.02054/) (2019)
- [FedGAN: Federated Generative Adversarial Networks for Distributed Data](https://mlsanity.com/paper/2006.07228/) (2020)
- [KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation](https://mlsanity.com/paper/2011.09757/) (2020)
- [Federated Multi-Target Domain Adaptation](https://mlsanity.com/paper/2108.07792/) (2021)
- [Private Federated Learning with Domain Adaptation](https://mlsanity.com/paper/1912.06733/) (2019)
- [Federated Contrastive Learning for Decentralized Unlabeled Medical Images](https://mlsanity.com/paper/2109.07504/) (2021)
- [Scanner Invariant Representations for Diffusion MRI Harmonization](https://mlsanity.com/paper/1904.05375/) (2019)
- [Federated Variational Learning for Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2108.08404/) (2021)
- [Heterogeneous Data-Aware Federated Learning](https://mlsanity.com/paper/2011.06393/) (2020)

## Built on by (most cited first, 10 of 10)

- [Federated Learning for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2306.05980/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classification](https://mlsanity.com/paper/2503.18981/) (2025)
- [Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement](https://mlsanity.com/paper/2604.04030/) (2026)
- [SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis](https://mlsanity.com/paper/2303.15965/) (2023)
- [A Survey on Federated Unlearning: Challenges and Opportunities](https://mlsanity.com/paper/2403.02437/) (2024)
- [Federated Impression for Learning with Distributed Heterogeneous Data](https://mlsanity.com/paper/2409.07351/) (2024)
- [Streamlined Federated Unlearning: Unite as One to Be Highly Efficient](https://mlsanity.com/paper/2412.00126/) (2024)
- [FedDAPL: Toward Client-Private Generalization in Federated Learning](https://mlsanity.com/paper/2509.23688/) (2025)
- [FeTTL: Federated Template and Task Learning for Multi-Institutional Medical Imaging](https://mlsanity.com/paper/2601.16302/) (2026)

## Abstract (arXiv)

The ability to combine data across scanners and studies is vital for neuroimaging, to increase both statistical power and the representation of biological variability. However, combining datasets across sites leads to two challenges: first, an increase in undesirable non-biological variance due to scanner and acquisition differences - the harmonisation problem - and second, data privacy concerns due to the inherently personal nature of medical imaging data, meaning that sharing them across sites may risk violation of privacy laws. To overcome these restrictions, we propose FedHarmony: a harmonisation framework operating in the federated learning paradigm. We show that to remove the scanner-specific effects, we only need to share the mean and standard deviation of the learned features, helping to protect individual subjects' privacy. We demonstrate our approach across a range of realistic data scenarios, using real multi-site data from the ABIDE dataset, thus showing the potential utility of our method for MRI harmonisation across studies. Our code is available at https://github.com/nkdinsdale/FedHarmony.