FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery

TL;DR

FedCARE introduces a low-overhead federated unlearning framework that effectively removes data influence while preserving model utility and resisting unintended relearning, using conflict-aware projection and class-level proxies.

Contribution

FedCARE presents a unified approach combining gradient ascent, data-free model inversion, and conflict-aware projection to improve federated unlearning efficiency and utility retention.

Findings

Achieves effective forgetting across multiple datasets and models.

Reduces relearning risk compared to existing methods.

Supports client, instance, and class-level unlearning with modest overhead.

Abstract

Federated learning (FL) enables collaborative model training without centralizing raw data, but privacy regulations such as the right to be forgotten require FL systems to remove the influence of previously used training data upon request. Retraining a federated model from scratch is prohibitively expensive, motivating federated unlearning (FU). However, existing FU methods suffer from high unlearning overhead, utility degradation caused by entangled knowledge, and unintended relearning during post-unlearning recovery. In this paper, we propose FedCARE, a unified and low overhead FU framework that enables conflict-aware unlearning and relearning-resistant recovery. FedCARE leverages gradient ascent for efficient forgetting when target data are locally available and employs data free model inversion to construct class level proxies of shared knowledge. Based on these insights, FedCARE integrates a pseudo-sample generator, conflict-aware projected gradient ascent for utility preserving unlearning, and a recovery strategy that suppresses rollback toward the pre-unlearning model. FedCARE supports client, instance, and class level unlearning with modest overhead. Extensive experiments on multiple datasets and model architectures under both IID and non-IID settings show that FedCARE achieves effective forgetting, improved utility retention, and reduced relearning risk compared to state of the art FU baselines.