<i>Harmonia</i>: A Unified Architecture for Efficient Deep Symbolic Regression

doi:10.1109/TCAD.2024.3443027

	Harmonia: A Unified Architecture for Efficient Deep Symbolic Regression
	Ma, Tianyun 1,2,3; Wen, Yuanbo 4; Song, Xinkai 4; Jin, Pengwei 3,4,5; Huang, Di 4; Han, Husheng 3,4,5; Nan, Ziyuan 3,4,5; Yu, Zhongkai 3,4,5; Peng, Shaohui 6; Zhao, Yongwei 4; Chen, Huaping 1; Du, Zidong 4,7; Hu, Xing 4,7; Guo, Qi 4
	2025-02-01
发表期刊	IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
ISSN	0278-0070
卷号	44 期号:2 页码:737-750
摘要	Symbolic regression (SR), the process of formulating a mathematical expression based on observed data points, is a fundamental task in artificial intelligence but is often hindered by its intense computational demands. Deep-learning-based SR methods (DSR) aim to alleviate these demands by breaking down the SR process into two stages: 1) neural network (NN) inference and 2) Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization. Although NN accelerators can expedite the NN stage, the performance of the BFGS optimization is compromised due to its poor performance for the variety of transcendental functions. Moreover, the distinct computational characteristics of NN inference and BFGS cause not only low hardware utilization but also significant area waste. To address these issues, we propose Harmonia, a unified architecture with the neural transcendental function unit (NTFU) and the Unified Array for efficient DSR. The NTFU utilizes the radial basis function network (RBFN) as a universal approximator for various transcendental functions, which significantly reduces the heavy transcendental function computation cost. We further propose an efficient training algorithm called random nonlinear optimization (RNO) to obtain a lightweight RBFN without accuracy loss. Moreover, Harmonia supports configurable dataflow which integrates the two computing stages into the Unified Array. Experimental results show that Harmonia achieves hardware utilization of 83.83%, on average. Compared to the GPU baseline, Harmonia achieves 4.8x speedup and 47.6x energy saving, alongside considerable low area cost.
关键词	Skeleton Optimization Graphics processing units Vectors Hardware Artificial neural networks Accuracy Deep symbolic regression (DSR) radial basis function network (RBFN) transcendental functions unified array
DOI	10.1109/TCAD.2024.3443027
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2022YFB4501603] ; NSF of China[U22A2028] ; NSF of China[U20A20227] ; NSF of China[61925208] ; NSF of China[62222214] ; NSF of China[62341411] ; NSF of China[62102398] ; NSF of China[62102399] ; NSF of China[62372436] ; NSF of China[62302478] ; NSF of China[62302482] ; NSF of China[62302483] ; NSF of China[62302480] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0660200] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0660201] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0660202] ; CAS Project for Young Scientists in Basic Research[YSBR-029] ; Youth Innovation Promotion Association CAS ; Xplore Prize
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Interdisciplinary Applications ; Engineering, Electrical & Electronic
WOS记录号	WOS:001405888600011
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40761
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Hu, Xing
作者单位	1.Univ Sci & Technol China, Hefei 230027, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Proc, Beijing 100190, Peoples R China 3.Cambricon Technol, Beijing 100191, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, SKL Proc, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 6.Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China 7.Shanghai Innovat Ctr Proc Technol, Shanghai 200235, Peoples R China
推荐引用方式 GB/T 7714	Ma, Tianyun,Wen, Yuanbo,Song, Xinkai,et al. Harmonia: A Unified Architecture for Efficient Deep Symbolic Regression[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2025,44(2):737-750.
APA	Ma, Tianyun.,Wen, Yuanbo.,Song, Xinkai.,Jin, Pengwei.,Huang, Di.,...&Guo, Qi.(2025).Harmonia: A Unified Architecture for Efficient Deep Symbolic Regression.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,44(2),737-750.
MLA	Ma, Tianyun,et al."Harmonia: A Unified Architecture for Efficient Deep Symbolic Regression".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 44.2(2025):737-750.