# Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy

arXiv: https://arxiv.org/abs/2510.07022 · HTML: https://mlsanity.com/paper/2510.07022/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Learning from History for Byzantine Robust Optimization](https://mlsanity.com/paper/2012.10333/) (2020)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information](https://mlsanity.com/paper/2210.10936/) (2022)
- [Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning](https://mlsanity.com/paper/2302.02069/) (2023)
- [DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks](https://mlsanity.com/paper/2105.06209/) (2021)
- [Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity](https://mlsanity.com/paper/2405.17462/) (2024)
- [Scalable Federated Unlearning via Isolated and Coded Sharding](https://mlsanity.com/paper/2401.15957/) (2024)

## Abstract (arXiv)

Machine unlearning is critical for enforcing data deletion rights like the "right to be forgotten." As a decentralized paradigm, Federated Learning (FL) also requires unlearning, but realistic implementations face two major challenges. First, fairness in Federated Unlearning (FU) is often overlooked. Exact unlearning methods typically force all clients into costly retraining, even those uninvolved. Approximate approaches, using gradient ascent or distillation, make coarse interventions that can unfairly degrade performance for clients with only retained data. Second, most FU evaluations rely on synthetic data assumptions (IID/non-IID) that ignore real-world heterogeneity. These unrealistic benchmarks obscure the true impact of unlearning and limit the applicability of current methods. We first conduct a comprehensive benchmark of existing FU methods under realistic data heterogeneity and fairness conditions. We then propose a novel, fairness-aware FU approach, Federated Cross-Client-Constrains Unlearning (FedCCCU), to explicitly address both challenges. FedCCCU offers a practical and scalable solution for real-world FU. Experimental results show that existing methods perform poorly in realistic settings, while our approach consistently outperforms them.