Closing the Generalization Gap in Parameter-efficient Federated Edge Learning
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_ | 1866912736110182400 |
|---|---|
| author | Du, Xinnong Lyu, Zhonghao Cao, Xiaowen Wen, Chunyang Cui, Shuguang Xu, Jie |
| author_facet | Du, Xinnong Lyu, Zhonghao Cao, Xiaowen Wen, Chunyang Cui, Shuguang Xu, Jie |
| contents | Federated edge learning (FEEL) provides a promising foundation for edge artificial intelligence (AI) by enabling collaborative model training while preserving data privacy. However, limited and heterogeneous local datasets, as well as resource-constrained deployment, severely degrade both model generalization and resource utilization, leading to a compromised learning performance. Therefore, we propose a parameter-efficient FEEL framework that jointly leverages model pruning and client selection to tackle such challenges. First, we derive an information-theoretic generalization statement that characterizes the discrepancy between training and testing function losses and embed it into the convergence analysis. It reveals that a larger local generalization statement can undermine the global convergence. Then, we formulate a generalization-aware average squared gradient norm bound minimization problem, by jointly optimizing the pruning ratios, client selection, and communication-computation resources under energy and delay constraints. Despite its non-convexity, the resulting mixed-integer problem is efficiently solved via an alternating optimization algorithm. Extensive experiments demonstrate that the proposed design achieves superior learning performance than state-of-the-art baselines, validating the effectiveness of coupling generalization-aware analysis with system-level optimization for efficient FEEL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_23282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Closing the Generalization Gap in Parameter-efficient Federated Edge Learning Du, Xinnong Lyu, Zhonghao Cao, Xiaowen Wen, Chunyang Cui, Shuguang Xu, Jie Machine Learning Distributed, Parallel, and Cluster Computing Information Theory Federated edge learning (FEEL) provides a promising foundation for edge artificial intelligence (AI) by enabling collaborative model training while preserving data privacy. However, limited and heterogeneous local datasets, as well as resource-constrained deployment, severely degrade both model generalization and resource utilization, leading to a compromised learning performance. Therefore, we propose a parameter-efficient FEEL framework that jointly leverages model pruning and client selection to tackle such challenges. First, we derive an information-theoretic generalization statement that characterizes the discrepancy between training and testing function losses and embed it into the convergence analysis. It reveals that a larger local generalization statement can undermine the global convergence. Then, we formulate a generalization-aware average squared gradient norm bound minimization problem, by jointly optimizing the pruning ratios, client selection, and communication-computation resources under energy and delay constraints. Despite its non-convexity, the resulting mixed-integer problem is efficiently solved via an alternating optimization algorithm. Extensive experiments demonstrate that the proposed design achieves superior learning performance than state-of-the-art baselines, validating the effectiveness of coupling generalization-aware analysis with system-level optimization for efficient FEEL. |
| title | Closing the Generalization Gap in Parameter-efficient Federated Edge Learning |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Information Theory |
| url | https://arxiv.org/abs/2511.23282 |