Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911120726425600 |
|---|---|
| author | Yang, Ming Li, Dongrun Wang, Xin Yu, Xiaoyang Wu, Xiaoming He, Shibo |
| author_facet | Yang, Ming Li, Dongrun Wang, Xin Yu, Xiaoyang Wu, Xiaoming He, Shibo |
| contents | Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To address these limitations, we propose FedMate, a method that implements bilateral optimization: On the server side, we construct a dynamic global prototype, with aggregation weights calibrated by holistic integration of sample size, current parameters, and future prediction; a category-wise classifier is then fine-tuned using this prototype to preserve global consistency. On the client side, we introduce complementary classification fusion to enable merit-based discrimination training and incorporate cost-aware feature transmission to balance model performance and communication efficiency. Experiments on five datasets of varying complexity demonstrate that FedMate outperforms state-of-the-art methods in harmonizing generalization and adaptation. Additionally, semantic segmentation experiments on autonomous driving datasets validate the method's real-world scalability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17954 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination Yang, Ming Li, Dongrun Wang, Xin Yu, Xiaoyang Wu, Xiaoming He, Shibo Machine Learning Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To address these limitations, we propose FedMate, a method that implements bilateral optimization: On the server side, we construct a dynamic global prototype, with aggregation weights calibrated by holistic integration of sample size, current parameters, and future prediction; a category-wise classifier is then fine-tuned using this prototype to preserve global consistency. On the client side, we introduce complementary classification fusion to enable merit-based discrimination training and incorporate cost-aware feature transmission to balance model performance and communication efficiency. Experiments on five datasets of varying complexity demonstrate that FedMate outperforms state-of-the-art methods in harmonizing generalization and adaptation. Additionally, semantic segmentation experiments on autonomous driving datasets validate the method's real-world scalability. |
| title | Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.17954 |