HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning
arXiv:2501.09934v3 Announce Type: replace Abstract: The rapid growth of AI-enabled Internet of Vehicles (IoV) calls for efficient Machine Learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence of Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in the literature on VEC-HFL is that vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial challenges. First, improper aggregation rule
The proliferation of AI-enabled Internet of Vehicles (IoV) and the need for efficient, decentralized machine learning solutions are driving innovation in hierarchical federated learning architectures.
This research addresses a critical challenge in IoV by enabling timely multi-model training, which is essential for deploying complex AI functionalities in highly mobile and data-distributed environments.
The focus expands from basic federated learning to managing multiple AI models concurrently on vehicle-edge-cloud systems, improving the operational efficiency and robustness of AI in connected vehicles.
- · Automotive industry
- · Edge computing providers
- · AI/ML developers
- · Telecommunications infrastructure
- · Inflexible centralized ML solutions
- · Legacy in-vehicle software architectures
More sophisticated and timely AI applications become feasible within connected vehicles, enhancing safety and autonomous capabilities.
Increased demand for robust edge computing hardware and network infrastructure to support distributed multi-model training.
The development of standardized protocols for hierarchical federated learning across different vehicle manufacturers and cloud providers.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG