Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.20218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908730419838976 |
|---|---|
| author | Yang, Jixiao Chen, Jinyu Huang, Zixiao Xu, Chengda Zhang, Chi Li, Sijia |
| author_facet | Yang, Jixiao Chen, Jinyu Huang, Zixiao Xu, Chengda Zhang, Chi Li, Sijia |
| contents | Federated learning across multi-cloud environments faces critical challenges, including non-IID data distributions, malicious participant detection, and substantial cross-cloud communication costs (egress fees). Existing Byzantine-robust methods focus primarily on model accuracy while overlooking the economic implications of data transfer across cloud providers. This paper presents Cost-TrustFL, a hierarchical federated learning framework that jointly optimizes model performance and communication costs while providing robust defense against poisoning attacks. We propose a gradient-based approximate Shapley value computation method that reduces the complexity from exponential to linear, enabling lightweight reputation evaluation. Our cost-aware aggregation strategy prioritizes intra-cloud communication to minimize expensive cross-cloud data transfers. Experiments on CIFAR-10 and FEMNIST datasets demonstrate that Cost-TrustFL achieves 86.7% accuracy under 30% malicious clients while reducing communication costs by 32% compared to baseline methods. The framework maintains stable performance across varying non-IID degrees and attack intensities, making it practical for real-world multi-cloud deployments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20218 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cost-TrustFL: Cost-Aware Hierarchical Federated Learning with Lightweight Reputation Evaluation across Multi-Cloud Yang, Jixiao Chen, Jinyu Huang, Zixiao Xu, Chengda Zhang, Chi Li, Sijia Machine Learning Federated learning across multi-cloud environments faces critical challenges, including non-IID data distributions, malicious participant detection, and substantial cross-cloud communication costs (egress fees). Existing Byzantine-robust methods focus primarily on model accuracy while overlooking the economic implications of data transfer across cloud providers. This paper presents Cost-TrustFL, a hierarchical federated learning framework that jointly optimizes model performance and communication costs while providing robust defense against poisoning attacks. We propose a gradient-based approximate Shapley value computation method that reduces the complexity from exponential to linear, enabling lightweight reputation evaluation. Our cost-aware aggregation strategy prioritizes intra-cloud communication to minimize expensive cross-cloud data transfers. Experiments on CIFAR-10 and FEMNIST datasets demonstrate that Cost-TrustFL achieves 86.7% accuracy under 30% malicious clients while reducing communication costs by 32% compared to baseline methods. The framework maintains stable performance across varying non-IID degrees and attack intensities, making it practical for real-world multi-cloud deployments. |
| title | Cost-TrustFL: Cost-Aware Hierarchical Federated Learning with Lightweight Reputation Evaluation across Multi-Cloud |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.20218 |