Survey on Federated Unlearning: Challenges and Opportunities

Abstract

Federated learning (FL), introduced in 2017, enables collaborative learning across mutually distrusting parties without sharing raw data, enabling privacy-preserving model training. However, emerging regulations and practical demands require models to be able to forget learned data, leading to growing interest in Machine Unlearning (MU). In the context of FL, many techniques developed for unlearning in centralized settings are not trivially applicable. This is due to interactivity, stochasticity, heterogeneity, and limited data accessibility. This has motivated a distinct research area of federated unlearning (FU). This survey provides the first practice-oriented synthesis of FU, foregrounding aspects often overlooked in prior surveys: data-distribution modeling (and non-IID simulation), dataset selection, and FL system configurations. We introduce a taxonomy that separates influence removal from performance recovery, and compare FU approaches across unlearning targets, aggregation assumptions, and reproducibility signals. By analyzing datasets, evaluation metrics, and code availability, we surface key trends that differentiate FU from centralized MU. We highlight challenges unique to FU, such as interactive training, stochastic client participation, and data isolation, and synthesize open problems around scalability, fairness, and unlearning in foundation models. Our survey aims to guide FU research by clarifying methodological gaps, system assumptions, and promising directions.