Literature Database Entry

wu2026certified

Hengliang Wu, Youming Tao, Anhao Zhou, Shuzhen Chen, Falko Dressler and Dongxiao Yu, "Certified Unlearning in Decentralized Federated Learning," Proceedings of 45th IEEE International Conference on Computer Communications (INFOCOM 2026), Tokyo, Japan, May 2026. (to appear)

Abstract

Driven by the right to be forgotten (RTBF), machine unlearning has become an essential requirement in privacy-preserving machine learning. However, its realization in decentralized federated learning (DFL) remains largely unexplored. In decentralized settings, clients communicate with their neighbors to update local models, which propagate and mix globally through the network. Consequently, when a client requests deletion, its influence has been implicitly embedded across the system, making it challenging to remove without centralized coordination. To address this, we propose a novel unlearning framework based on Newton-style updates. Our approach first quantifies the mixed influence during training. Then, using curvature information of the loss landscape with respect to the target data, we construct corrective model updates with Newton-style approximations. To improve scalability, we approximate second-order information using the Fisher information matrices. These updates are further perturbed with carefully calibrated noise to ensure privacy, and are broadcast through the network to remove residual influence from all clients. We theoretically guarantees that our method satisfies the formal certified unlearning definition, ensuring model indistinguishability. Additionally, we establish utility bounds showing that the unlearned model remains close to the retrained one. Extensive experiments across various decentralized settings validate the effectiveness and efficiency of our framework.

Quick access

Authors' Version PDF (PDF on this web site)
BibTeX BibTeX

Contact

Hengliang Wu
Youming Tao
Anhao Zhou
Shuzhen Chen
Falko Dressler
Dongxiao Yu

BibTeX reference

@inproceedings{wu2026certified,
    author = {Wu, Hengliang and Tao, Youming and Zhou, Anhao and Chen, Shuzhen and Dressler, Falko and Yu, Dongxiao},
    note = {to appear},
    title = {{Certified Unlearning in Decentralized Federated Learning}},
    publisher = {IEEE},
    address = {Tokyo, Japan},
    booktitle = {45th IEEE International Conference on Computer Communications (INFOCOM 2026)},
    month = {5},
    year = {2026},
   }
   
   

Copyright notice

Links to final or draft versions of papers are presented here to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or distributed for commercial purposes without the explicit permission of the copyright holder.

The following applies to all papers listed above that have IEEE copyrights: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

The following applies to all papers listed above that are in submission to IEEE conference/workshop proceedings or journals: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

The following applies to all papers listed above that have ACM copyrights: ACM COPYRIGHT NOTICE. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Publications Dept., ACM, Inc., fax +1 (212) 869-0481, or permissions@acm.org.

The following applies to all SpringerLink papers listed above that have Springer Science+Business Media copyrights: The original publication is available at www.springerlink.com.

This page was automatically generated using BibDB and bib2web.

Last modified: 2026-04-27