On Resilient and Efficient Linear Secure Aggregation in Hierarchical Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915738005012480 |
|---|---|
| author | Weng, Shudi Zhang, Xiang Zhao, Yizhou Caire, Giuseppe Xiao, Ming Skoglund, Mikael |
| author_facet | Weng, Shudi Zhang, Xiang Zhao, Yizhou Caire, Giuseppe Xiao, Ming Skoglund, Mikael |
| contents | In this paper, we study the fundamental limits of hierarchical secure aggregation under unreliable communication. We consider a hierarchical network where each client connects to multiple relays, and both client-to-relay and relay-to-server links are intermittent. Under this setting, we characterize the minimum communication and randomness costs required to achieve robust secure aggregation. We then propose an optimal protocol that attains these minimum costs, and establish its optimality through a matching converse proof. In addition, we introduce an improved problem formulation that bridges the gap between existing information-theoretic secure aggregation protocols and practical real-world federated learning problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12853 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On Resilient and Efficient Linear Secure Aggregation in Hierarchical Federated Learning Weng, Shudi Zhang, Xiang Zhao, Yizhou Caire, Giuseppe Xiao, Ming Skoglund, Mikael Distributed, Parallel, and Cluster Computing In this paper, we study the fundamental limits of hierarchical secure aggregation under unreliable communication. We consider a hierarchical network where each client connects to multiple relays, and both client-to-relay and relay-to-server links are intermittent. Under this setting, we characterize the minimum communication and randomness costs required to achieve robust secure aggregation. We then propose an optimal protocol that attains these minimum costs, and establish its optimality through a matching converse proof. In addition, we introduce an improved problem formulation that bridges the gap between existing information-theoretic secure aggregation protocols and practical real-world federated learning problems. |
| title | On Resilient and Efficient Linear Secure Aggregation in Hierarchical Federated Learning |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.12853 |