AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression

Minh-Duong Nguyen, Senura Wanasekara, Le-Tuan Nguyen, Quoc-Viet Pham, Ken-Tye Yong, Nguyen H. Tran, Dung D. Le

CVPR 2026 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add on-server gradient-matching unlearning after the L2U stage (ablation)FOUL · PACSforget accuracy: 69.53 -> 70.97Hurt
add on-server gradient-matching unlearning after the L2U stage (ablation)FOUL · PACSretain accuracy: 93.11 -> 92.33No clear effect
add on-server gradient-matching unlearning after the L2U stage (ablation)FOUL · TerraIncognitatest accuracy: 38.16 -> 39.16Improved
use FOUL instead of retraining from scratch on retain clientsFedAvg · PACSretain accuracy: 82.84 -> 92.33Improved
use FOUL instead of retraining from scratch on retain clientsFedAvg · PACStest accuracy: 77.45 -> 76.43No clear effect
use FOUL instead of approximate unlearning baselines such as FUSEDFedAvg · PACSforget accuracy: 75.94 -> 70.97Improved
use FOUL instead of approximate unlearning baselinesFedAvg · PACSMIA: 50.02 -> 51.93Hurt
use FOUL instead of FUSEDFedAvg · PACScommunication per round (MB): 0.98 -> 16.02Hurt
use FOUL instead of retrainingFedAvg · PACScomputation (FLOPs): 5.81e16 -> 2.35e16Improved
use on-server gradient matching instead of naive FedAvg retrainingFedAvg · PACStime-to-forget: 0.13 -> 0.32Improved
unlearn only the non-causal featurizer during unlearningFOUL · PACSretain accuracy: 82.84 -> 92.33Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy