FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909004925501440 |
|---|---|
| author | Kou, Zhiqiang Wu, Junxiang Huang, Wenke He, Wenwen Xie, Ming-Kun Wang, Changwei Jia, Yuheng Jiang, Di Liu, Yang Geng, Xin Yang, Qiang |
| author_facet | Kou, Zhiqiang Wu, Junxiang Huang, Wenke He, Wenwen Xie, Ming-Kun Wang, Changwei Jia, Yuheng Jiang, Di Liu, Yang Geng, Xin Yang, Qiang |
| contents | Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions remains challenging. Due to client-specific label spaces and varying co-occurrence patterns, correlations learned by individual clients inevitably deviate from the global structure, a phenomenon we term label correlation drift. To address this, we propose FedHarmony, a framework that harmonizes heterogeneous label correlations across clients. It introduces consensus correlation, capturing agreement among other clients and serving as a global teacher to correct biased local estimates. During aggregation, FedHarmony evaluates each client by both data size and correlation quality, assigning weights accordingly. Moreover, we develop an accelerated optimization algorithm for FedHarmony and theoretically establish faster convergence without sacrificing accuracy. Experiments on real-world federated multi-label datasets show that FedHarmony consistently outperforms state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_28024 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning Kou, Zhiqiang Wu, Junxiang Huang, Wenke He, Wenwen Xie, Ming-Kun Wang, Changwei Jia, Yuheng Jiang, Di Liu, Yang Geng, Xin Yang, Qiang Machine Learning Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions remains challenging. Due to client-specific label spaces and varying co-occurrence patterns, correlations learned by individual clients inevitably deviate from the global structure, a phenomenon we term label correlation drift. To address this, we propose FedHarmony, a framework that harmonizes heterogeneous label correlations across clients. It introduces consensus correlation, capturing agreement among other clients and serving as a global teacher to correct biased local estimates. During aggregation, FedHarmony evaluates each client by both data size and correlation quality, assigning weights accordingly. Moreover, we develop an accelerated optimization algorithm for FedHarmony and theoretically establish faster convergence without sacrificing accuracy. Experiments on real-world federated multi-label datasets show that FedHarmony consistently outperforms state-of-the-art methods. |
| title | FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.28024 |