AI Paper Atlas

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

Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew

Can Peng, Yuyuan Liu, YINGYU YANG, Pramit Saha, Qianye Yang, J. Noble

ECCV 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 2 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 predefined ETF classifier alone (ablation)baseline FL model · DermaMNIST (beta=0.1)macro-F1: 40.69 -> 33.35Hurt
add LADM class-specific extraction on top of ETF classifier (ablation)ETF classifier · DermaMNIST (beta=0.1)macro-F1: 33.35 -> 47.95Improved
add L_Neg and L_Pos regularisation (ablation)ETF + LADM · DermaMNIST (beta=0.1)macro-F1: 47.95 -> 51.38Improved
add only L_Neg (without L_Pos) (ablation)ETF + LADM · DermaMNIST (beta=0.1)macro-F1: 47.95 -> 45.06Hurt
add only L_Pos (without L_Neg) (ablation)ETF + LADM · DermaMNIST (beta=0.1)macro-F1: 47.95 -> 49.84Improved
add ETF classifier alone (ablation)baseline FL model · CIFAR-10 (beta=0.5)macro-F1: 40.65 -> 15.29Hurt
add LADM on top of ETF classifier (ablation)ETF classifier · CIFAR-10 (beta=0.5)macro-F1: 15.29 -> 44.64Improved
add L_Neg and L_Pos regularisation (ablation)ETF + LADM · CIFAR-10 (beta=0.5)macro-F1: 44.64 -> 49.22Improved
use fixed ETF queries instead of learnable random queries in LADM (ablation)LADM · DermaMNIST (beta=0.1)macro-F1: 47.94 -> 47.95No clear effect
use fixed ETF queries instead of learnable ETF-initialised queries (ablation)LADM · DermaMNIST (beta=0.1)micro-F1: 53.37 -> 60.49Improved
use fixed ETF queries instead of learnable ETF-initialised queries (ablation)LADM · CIFAR-10 (beta=0.5)macro-AUC: 86.26 -> 85.84Mixed
use FedNCA-ML instead of second-best methodFedLGT / SphereFed · CIFAR-10 (beta=0.5)macro-AUC: 83.63 -> 87.55Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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