AI Paper Atlas

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

FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning

Zhiqiang Kou, Junxiang Wu, Wenke Huang, Wenwen He, Ming-Kun Xie, Changwei Wang, Yuheng Jia, Di Jiang, Yang Liu, Xin Geng, Qiang Yang

CVPR 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 expert-guided correlation loss (ECL) (ablation)FedAvg · COCO-80mAP: 63.4 -> 69.5Improved
add expert-guided correlation loss (ECL) (ablation)FedAvg · FLAIRmAP: 35.4 -> 46.4Improved
add correlation-aware aggregation (CAA) (ablation)FedAvg+ECL · COCO-80mAP: 69.5 -> 71.2Improved
add correlation-aware aggregation (CAA) (ablation)FedAvg+ECL · FLAIRmAP: 46.4 -> 47.0Improved
add correlation-aware aggregation (CAA) (ablation)FedAvg+ECL · COCO-80OP: 79.2 -> 78.5Hurt
add correlation-aware aggregation (CAA) (ablation)FedAvg+ECL · FLAIRCR: 40.9 -> 39.3Hurt
add correlation-aware aggregation (CAA) (ablation)FedAvg+ECL · FLAIROF1: 73.0 -> 74.3Improved
add block-wise clustering optimization (ablation)FedHarmony · COCO-80mAP: 71.2 -> 72.4No clear effect
add block-wise clustering optimization (ablation)FedHarmony · VOC2007mAP: 86.1 -> 87.0No clear effect
add block-wise clustering optimization (ablation)FedHarmony · FLAIRmAP: 47.0 -> 48.0No clear effect
add block-wise clustering optimization (ablation)FedHarmony · FLAIRcumulative training time (10 rounds): 56:19 -> 40:22Improved
add block-wise clustering optimization (ablation)FedHarmony · VOC2007cumulative training time (10 rounds): 17:09 -> 11:43Improved

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