Split Learning in 6G Edge Networks
Разделённое обучение в периферийных сетях 6G
2024-05-13
SCID: 54.1/szuwa9d2
Discuss with AI
6G edge networksmodel placement and migrationresource managementsplit edge learningsplit learning
Figures from the paper
Abstract (AI)
With the proliferation of distributed edge computing resources, the 6G mobile network will evolve into a network for connected intelligence. Along this line, the proposal to incorporate federated learning into the mobile edge has gained considerable interest in recent years. However, the deployment of federated learning faces substantial challenges as massive resource-limited IoT devices can hardly support on-device model training. This leads to the emergence of split learning (SL) which enables servers to handle the major training workload while still enhancing data privacy. In this article, we offer a brief overview of SL and articulate its seamless integration with wireless edge networks. We begin by illustrating the tailored 6G architecture to support split edge learning (SEL). Then, we examine the critical design issues for SEL, including resource-efficient learning frameworks and resource management strategies under a single edge server. Furthermore, from a networking perspective, we expand the scope to multi-edge scenarios, exploring multiedge collaboration and model placement/migration. Finally, we discuss open problems for SEL, including convergence analysis, asynchronous SL, and label privacy preservation.
Key Findings
1
For multi-edge environments, the paper examines edge collaboration and model placement or migration as mechanisms for scalable split learning.
2
For single-edge-server deployments, key design challenges include developing resource-efficient learning frameworks and effective resource-management strategies.
3
Open research problems include convergence analysis, asynchronous split learning, and preservation of label privacy.
4
Split learning addresses federated learning’s difficulty on resource-limited IoT devices by assigning most model-training computation to edge servers while preserving data privacy.
5
The paper outlines a 6G architecture tailored to support split edge learning within connected-intelligence networks.
Research Object
split learning in 6G wireless edge networks, including single- and multi-edge server scenarios
Research Subject
integration, resource-efficient operation, resource management, collaboration, model placement and migration, and privacy and convergence issues of split edge learning
Publication Details
Publication Date
2024-05-13
Journal
Publisher
ISSN
Cited by
199
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Cited by4
Efficient Parallel Split Learning Over Resource-Constrained Wireless Edge Networks2024
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey2026
Toward Edge General Intelligence With Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration2025
Computational Architectures for 6G Networks: Integrating Distributed Computing and Edge Artificial Intelligence2026