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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add expert-guided correlation loss (ECL) (ablation) | FedAvg · COCO-80 | mAP: 63.4 -> 69.5 | Improved |
| add expert-guided correlation loss (ECL) (ablation) | FedAvg · FLAIR | mAP: 35.4 -> 46.4 | Improved |
| add correlation-aware aggregation (CAA) (ablation) | FedAvg+ECL · COCO-80 | mAP: 69.5 -> 71.2 | Improved |
| add correlation-aware aggregation (CAA) (ablation) | FedAvg+ECL · FLAIR | mAP: 46.4 -> 47.0 | Improved |
| add correlation-aware aggregation (CAA) (ablation) | FedAvg+ECL · COCO-80 | OP: 79.2 -> 78.5 | Hurt |
| add correlation-aware aggregation (CAA) (ablation) | FedAvg+ECL · FLAIR | CR: 40.9 -> 39.3 | Hurt |
| add correlation-aware aggregation (CAA) (ablation) | FedAvg+ECL · FLAIR | OF1: 73.0 -> 74.3 | Improved |
| add block-wise clustering optimization (ablation) | FedHarmony · COCO-80 | mAP: 71.2 -> 72.4 | No clear effect |
| add block-wise clustering optimization (ablation) | FedHarmony · VOC2007 | mAP: 86.1 -> 87.0 | No clear effect |
| add block-wise clustering optimization (ablation) | FedHarmony · FLAIR | mAP: 47.0 -> 48.0 | No clear effect |
| add block-wise clustering optimization (ablation) | FedHarmony · FLAIR | cumulative training time (10 rounds): 56:19 -> 40:22 | Improved |
| add block-wise clustering optimization (ablation) | FedHarmony · VOC2007 | cumulative training time (10 rounds): 17:09 -> 11:43 | Improved |
Closest papers by meaning
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.89)
- Progressive Distribution Matching for Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.88)
- Language-Guided Transformer for Federated Multi-Label Classification (AAAI 2024 · similarity 0.87)
- FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning (AAAI 2024 · similarity 0.87)
- Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch (CVPR 2025 · similarity 0.87)
- FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels (AAAI 2024 · similarity 0.86)
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.
