AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Client-level Active Error Correction in Distributed Learning

Kwang In Kim

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 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
use GPAEC gradient-GP client selection instead of random selectionclient-level AEC · CIFAR100 / C1M / EMNIST (stage 11)accuracy: C1M 53.99 -> 55.85; EMNIST 81.15 -> 82.42; CIFAR100 59.34 -> 60.51Improved
select clients by highest average loss instead of GPAECclient-level AEC baseline · C1M early stage 1accuracy: Rand 49.08 -> Loss 48.70 (GPAEC 51.19)Hurt
rank-combine GP inconsistency with loss deviation instead of loss aloneGPAEC · first stage client selectionfraction rational clients selected: 42.2% (Loss) -> 88.9%Improved
replace GP inconsistency with distance from mean gradient (ablation)GPAEC · CIFAR10accuracy at stage 11: 85.64 -> 84.47Hurt
replace GP inconsistency with distance from median gradient (ablation)GPAEC · CIFAR10accuracy at stage 11: 85.64 -> 85.08Hurt
use small 3-conv CNN instead of ResNet50 (ablation)GPAEC · Kuzushiji49accuracy at stage 11: GPAEC 47.81 vs Rand 46.43Improved
select L=60 clients per stage (ablation)GPAEC · CIFAR100accuracy at stage 11: Rand 61.35 -> GPAEC 61.81Improved
select L=20 clients per stage (ablation)GPAEC · TImgNetaccuracy at stage 11: Rand 50.83 -> GPAEC 52.64Improved
unreliable clients clean labels but inflate loss (ablation)GPAEC · C1Maccuracy at stage 11: Rand 54.77 -> GPAEC 56.33Improved
select by entropy instead of GPAECclient-level AEC baseline · C1Maccuracy at stage 11: Rand 53.99 -> Ent 52.58Hurt
spread budget uniformly over all clients instead of selectingclient-level AEC baseline · CIFAR10accuracy at stage 11: Rand 84.74 -> Uniform 85.02No clear effect

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