Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.12544 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915879430651904 |
|---|---|
| author | Peng, Can Liu, Yuyuan Yang, Yingyu Saha, Pramit Yang, Qianye Noble, J. Alison |
| author_facet | Peng, Can Liu, Yuyuan Yang, Yingyu Saha, Pramit Yang, Qianye Noble, J. Alison |
| contents | Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but remains challenging when client data are highly heterogeneous. These challenges are further amplified in multi-label scenarios, where inter-label dependencies and mismatches between local and global label relationships introduce additional optimization conflicts. While most FL studies focus on single-label classification, many real-world applications are inherently multi-label and often exhibit severe label skew across clients. To address this important yet underexplored problem, we propose FedNCA-ML, a novel FL framework that aligns client representations and learns discriminative, well-clustered features inspired by Neural Collapse (NC) theory. NC describes an ideal latent geometry where each class's features collapse to their mean, forming a maximally separated simplex. FedNCA-ML further introduces an attention-based module to extract class-specific representations, enabling more balanced learning under heavy label imbalance. These class-wise representations are then aligned via a shared NC-inspired structure, mitigating inter-client conflicts induced by heterogeneous local data and inconsistent label dependencies. In addition, we design regularisation losses to encourage compact and consistent feature clustering in the latent space. Experiments on five benchmark datasets under nine FL settings demonstrate the effectiveness of the proposed method, achieving improvements of up to 3.92% in class-wise AUC and 4.93% in class-wise F1 score. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12544 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew Peng, Can Liu, Yuyuan Yang, Yingyu Saha, Pramit Yang, Qianye Noble, J. Alison Computer Vision and Pattern Recognition Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but remains challenging when client data are highly heterogeneous. These challenges are further amplified in multi-label scenarios, where inter-label dependencies and mismatches between local and global label relationships introduce additional optimization conflicts. While most FL studies focus on single-label classification, many real-world applications are inherently multi-label and often exhibit severe label skew across clients. To address this important yet underexplored problem, we propose FedNCA-ML, a novel FL framework that aligns client representations and learns discriminative, well-clustered features inspired by Neural Collapse (NC) theory. NC describes an ideal latent geometry where each class's features collapse to their mean, forming a maximally separated simplex. FedNCA-ML further introduces an attention-based module to extract class-specific representations, enabling more balanced learning under heavy label imbalance. These class-wise representations are then aligned via a shared NC-inspired structure, mitigating inter-client conflicts induced by heterogeneous local data and inconsistent label dependencies. In addition, we design regularisation losses to encourage compact and consistent feature clustering in the latent space. Experiments on five benchmark datasets under nine FL settings demonstrate the effectiveness of the proposed method, achieving improvements of up to 3.92% in class-wise AUC and 4.93% in class-wise F1 score. |
| title | Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.12544 |