期刊
NATURE COMMUNICATIONS
卷 13, 期 1, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41467-022-32020-w
关键词
-
资金
- National Research Foundation, Singapore under its Strategic Capability Research Centres Funding Initiative: Strategic Centre for Research in Privacy-Preserving Technologies Systems
- Nanyang Technological University (NTU) Startup Grant
- Singapore Ministry of Education Academic Research Fund
- National Research Foundation, Singapore
- Infocomm Media Development Authority under its Future Communications Research & Development Programme
- SUTD [SRG-ISTD-2021-165]
- U.S. National Science Foundation [CCF-1908308]
- Singapore Ministry of Education (MOE) Tier 1 [RG16/20]
- National Natural Science Foundation of China [U21A20444, 61971366]
This paper proposes a leading federated neuromorphic learning (LFNL) technique, which is a decentralized energy-efficient brain-inspired computing method based on spiking neural networks. The LFNL enables edge devices to collaborate in training a global model using a brain-like physiological structure while preserving privacy.
Designing energy-efficient computing solution for the implementation of AI algorithms in edge devices remains a challenge. Yang et al. proposes a decentralized brain-inspired computing method enabling multiple edge devices to collaboratively train a global model without a fixed central coordinator. In order to realize the full potential of wireless edge artificial intelligence (AI), very large and diverse datasets will often be required for energy-demanding model training on resource-constrained edge devices. This paper proposes a lead federated neuromorphic learning (LFNL) technique, which is a decentralized energy-efficient brain-inspired computing method based on spiking neural networks. The proposed technique will enable edge devices to exploit brain-like biophysiological structure to collaboratively train a global model while helping preserve privacy. Experimental results show that, under the situation of uneven dataset distribution among edge devices, LFNL achieves a comparable recognition accuracy to existing edge AI techniques, while substantially reducing data traffic by >3.5x and computational latency by >2.0x. Furthermore, LFNL significantly reduces energy consumption by >4.5x compared to standard federated learning with a slight accuracy loss up to 1.5%. Therefore, the proposed LFNL can facilitate the development of brain-inspired computing and edge AI.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据