Paper
15 August 2023 Distributed training for spatio-temporal neural networks
Yanqiu Yang, Xin Yan, Zhongjie Lei
Author Affiliations +
Proceedings Volume 12719, Second International Conference on Electronic Information Technology (EIT 2023); 127194D (2023) https://doi.org/10.1117/12.2685449
Event: Second International Conference on Electronic Information Technology (EIT 2023), 2023, Wuhan, China
Abstract
For the training of spatio-temporal sensing data, most of the existing methods are centralized or combined with federated learning, but in some scenarios only fully distributed training can be performed. And the existing methods basically assume that the topology of the agent is fixed, but sometimes the topology changes dynamically. Therefore, this paper combines the (sub)gradient projection method to realize a distributed training method for spatio-temporal sensing data. Our method is not only suitable for scenarios where the agent topology is fixed, but also for scenarios where the topology changes dynamically.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yanqiu Yang, Xin Yan, and Zhongjie Lei "Distributed training for spatio-temporal neural networks", Proc. SPIE 12719, Second International Conference on Electronic Information Technology (EIT 2023), 127194D (15 August 2023); https://doi.org/10.1117/12.2685449
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Sensor networks

Neural networks

Sensors

Transformers

Back to Top