FUPareto: Bridging the Forgetting-Utility Gap in Federated Unlearning via Pareto Augmented Optimization

TL;DR

FUPareto introduces a Pareto-optimized framework for federated unlearning that effectively balances data removal, utility preservation, and security against attacks, while supporting concurrent multi-client unlearning.

Contribution

The paper proposes FUPareto, a novel Pareto-augmented optimization framework that enhances federated unlearning by improving efficiency, security, and multi-client support.

Findings

Outperforms existing methods in unlearning efficacy

Reduces vulnerability to Membership Inference Attacks

Supports effective concurrent multi-client unlearning

Abstract

Federated Unlearning (FU) aims to efficiently remove the influence of specific client data from a federated model while preserving utility for the remaining clients. However, three key challenges remain: (1) existing unlearning objectives often compromise model utility or increase vulnerability to Membership Inference Attacks (MIA); (2) there is a persistent conflict between forgetting and utility, where further unlearning inevitably harms retained performance; and (3) support for concurrent multi-client unlearning is poor, as gradient conflicts among clients degrade the quality of forgetting. To address these issues, we propose FUPareto, an efficient unlearning framework via Pareto-augmented optimization. We first introduce the Minimum Boundary Shift (MBS) Loss, which enforces unlearning by suppressing the target class logit below the highest non-target class logit; this can improve the unlearning efficiency and mitigate MIA risks. During the unlearning process, FUPareto performs Pareto improvement steps to preserve model utility and executes Pareto expansion to guarantee forgetting. Specifically, during Pareto expansion, the framework integrates a Null-Space Projected Multiple Gradient Descent Algorithm (MGDA) to decouple gradient conflicts. This enables effective, fair, and concurrent unlearning for multiple clients while minimizing utility degradation. Extensive experiments across diverse scenarios demonstrate that FUPareto consistently outperforms state-of-the-art FU methods in both unlearning efficacy and retained utility.