Logo image
United Split Federated Learning with Evolutionary Game Approach
會議論文集

United Split Federated Learning with Evolutionary Game Approach

H.-T. Huang 和 T.-C. Chiu
Proceedings - IEEE Global Communications Conference, GLOBECOM, 頁碼.4505-4510
2025
Web of Science ID: WOS:001810917600206

摘要

Edge intelligence Evolutionary computing Federated learning Split learning Artificial intelligence Computation theory Computer games Contrastive Learning Edge computing Evolutionary algorithms Learning systems Based clustering Evolutionary games Game approach Game-Based Intelligent decisions Learning frameworks Modeling accuracy Game Theory Knowledge Management
Edge intelligence empowered by 6G is a promising technique for realizing AIoT applications. However, making intelligent decisions through distributed training across various mobile devices, considering model accuracy, system heterogeneity, and training latency, is still an open challenge. In this paper, we propose a United Split Federated Learning (U-SFL), a two-level collaboration framework with a "first-sequential-then-parallel"principle that integrates sequential split learning within clusters and parallel training across clusters to achieve fine-grained and coarse-grained knowledge sharing jointly. Furthermore, we design an evolutionary game-based clustering approach that enables devices to identify the environmental fitness of the cluster and self-organize themselves into a suitable cluster with a theoretical evolutionary equilibrium proof. By integrating the U-SFL framework with evolutionary game-based clustering, we effectively mitigate the overhead of sequential training, achieving faster convergence with fewer clusters and reversing the conventional belief that only higher parallelism can reduce training latency. The experimental results show that the U-SFL framework outperforms the SOTA edge intelligence frameworks and preserves optimized training latency in a large-scale heterogeneous split federated learning system. © 2025 IEEE.

檔案與連結 (1)

url
https://www.scopus.com/inward/record.uri?eid=2-s2.0-105036271634&doi=10.1109%2fGLOBECOM59602.2025.11432352&partnerID=40&md5=a2ccc174aa234c684cca1aa07ec6a776檢視

相關連結

指標

3 檢視次數

詳細資料

Logo image