Skip to content

MMT: Achieving Exact Federated Unlearning with Improved Post-unlearning Performance

Oct 2026 · Machine-mediated learning · Vol 115 · 1 citation · 71 references
Computer Science

TL;DR

Two exact federated unlearning algorithms are proposed, Bi-Models Training (bmt) and Multi-Models Training (mmt), that ensure immediate exact unlearning by design while achieving better performance post-unlearning.

View source

Similar papers

Open access 2026

Practical Federated Unlearning: A Target Client-Driven Approach to Model Forgetting

PFU is proposed, a target client-driven approach to model forgetting with only a single round of interaction between the target client and the aggregation server during the unlearning stage, which achieves effective unlearning of the data knowledge while preventing catastrophic forgetting.

Lei Tian, Fei-Long Lin, Zhan Qin et al. · 0 citations
#machine learning Preprint Oct 2026

Not All Retained Clients Are Equal: Client Selection for Federated Unlearning

Federated unlearning (FU) aims to remove a designated target client's influence from a trained model without the prohibitive cost of retraining from scratch. Existing methods largely treat unlearning as a post-hoc, stateless operation, overlooking that client influence is path-dependent: contributions made during train...

Thanh Linh Nguyen, Quoc-Viet Pham · 0 citations
#federated learning Open access Dec 2026

Efficient and Effective Federated Unlearning via Adaptive Data Partitioning

This paper first establishes inter-shard relationships via a personalized aggregation mechanism, which significantly alleviates the model accuracy degradation caused by disjoint sharding and non-IID data, while still ensuring confined unlearning overhead.

Zhi-Gang Wang, Jia-Hao Li, Ning Wang et al. · 0 citations

OPFL: Optimistic Verification of Federated Learning via Empirical Boundary

OPFL calibrates an empirical boundary offline and uses it to distinguish benign numerical deviations from malicious manipulation, and adopts optimistic verification by post auditing only sampled training steps to reduce the cost of expensive MPC replay.

Hong-Xu Su, Jian-Zhu Yao, Xue-Chao Wang et al. · 0 citations
Sep 2026

ZMASA: Robust Aggregation for Federated Learning Against Byzantine Attacks.

A theoretical analysis showing that, under bounded retained residuals, the aggregation error is controlled by the candidate-set Byzantine contamination, the magnitude of retained Byzantine residuals, and the stability of attention weights, achieves competitive or superior robustness compared with classical and recent r...

Shu-Juan Tian, Shu-Huan Xiang, Gang Liu et al. · 0 citations
#machine learning Conference Open access Sep 2026

Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning

Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce delays in aggregating the local models and hence, the convergence of the global model. Ther...

Muzaffer Citir, Hiroki Nishikawa, Sangyoung Park · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.