Hierarchical, Distributed and Brain-Inspired Learning for Internet of Things Systems

被引:2
作者
Imani, Mohsen [1 ]
Kim, Yeseong [2 ]
Khaleghi, Behnam [3 ]
Morris, Justin [4 ]
Alimohamadi, Haleh [5 ]
Imani, Farhad [6 ]
Latapie, Hugo [7 ]
机构
[1] UC Irvine, Irvine, CA 92697 USA
[2] DGIST, Daegu, South Korea
[3] Qualcomm, San Diego, CA USA
[4] Calif State Univ San Marcos, San Marcos, TX USA
[5] UC Los Angeles, Los Angeles, CA USA
[6] Univ Connecticut, Storrs, CT USA
[7] CISCO, San Jose, CA USA
来源
2023 IEEE 43RD INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, ICDCS | 2023年
基金
美国国家科学基金会; 新加坡国家研究基金会;
关键词
NETWORK;
D O I
10.1109/ICDCS57875.2023.00083
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose EdgeHD, a hierarchy-aware learning solution that performs online training and inference in a highly distributed, cost-effective way. We use brain-inspired hyperdimensional (HD) computing as the key enabler. HD computing performs the computation tasks on a high-dimensional space to emulate functionalities of the human memory, such as inter-data relationship reasoning and information aggregation. EdgeHD exploits HD computing to effectively learn the classification models on individual devices and combine the models through the hierarchical IoT nodes without high communication costs. We also propose a hardware design that accelerates EdgeHD on low-power FPGA platforms. We evaluated EdgeHD for a wide range of real-world classification applications. The evaluation shows that EdgeHD provides highly efficient computation with reduced communication. For example, EdgeHD achieves on average 3.4x and 11.7x (1.9x and 7.8x) speedup and energy efficiency improvement during the training (inference) as compared to the centralized learning approach. It reduces the communication costs by 85% for the training and 78% for the inference.
引用
收藏
页码:511 / 522
页数:12
相关论文
共 52 条
[1]  
Aazam M, 2014, 2014 IEEE NINTH INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING (IEEE ISSNIP 2014)
[2]  
Abadi M., 2019, CoRR abs/1603.04467. arXiv: 1603 . 04467, DOI DOI 10.48550/ARXIV.1603.04467
[3]   Mobile Edge Computing: A Survey [J].
Abbas, Nasir ;
Zhang, Yan ;
Taherkordi, Amir ;
Skeie, Tor .
IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (01) :450-465
[4]  
Angelova A, 2005, PROC CVPR IEEE, P494
[5]  
Anguita D., 2012, Ambient Assisted Living and Home Care, P216, DOI [DOI 10.1016/J.PATCOG.2020.107561, DOI 10.1007/978-3-642-35395-630]
[6]  
[Anonymous], Huawei ai chip
[7]  
[Anonymous], 2007, Advances in neural information processing systems
[8]  
[Anonymous], PECAN STREET DATAPOR
[9]  
Bagdasaryan E., 2018, arXiv
[10]   DARL: Distributed Reconfigurable Accelerator for Hyperdimensional Reinforcement Learning [J].
Chen, Hanning ;
Issa, Mariam ;
Ni, Yang ;
Imani, Mohsen .
2022 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, ICCAD, 2022,