基于图注意力网络的模拟电路结构标注

doi:10.3969/j.issn.1006-2475.2025.06.016

摘要/Abstract

摘要： 摘要：电路结构的自动化标注能够生成层次化的模拟电路网络结构表达，从而推动模拟电路设计自动化任务的发展。本文利用一种基于图注意力网络的图模型，将电路网表转换为图结构，提出一种特征提取策略，学习并预测网表中节点组成的电路结构，同时提出一种快速生成大量SPICE电路网表的方法，为图模型的训练提供充足的数据。实验分别对比了图卷积网络、图同构网络以及GraphSAGE在同一数据集上的识别效果，结果显示本文模型在准确率、精确度和平均精确率3个指标上均优于其他模型，分别达到了90.9%、91.6%和91.9%。表明了本文模型在捕捉电路连接关系方面的优越性，尤其是在处理复杂电路图时的有效性。

关键词: 关键词：自动化标注, 图注意力网络, 电路结构, 特征提取 ,

Abstract:
Abstract：Automated annotation of circuit structures can generate hierarchical representations of analog circuit networks， thereby advancing the development of automated analog circuit design tasks. This paper introduces a graph attention network-based model that transforms circuit netlists into graph structures， proposes a feature extraction strategy to learn and predict the circuit structures composed of nodes in the netlists， and presents a method for quickly generating a large number of SPICE circuit netlists to provide ample data for training the graph model. Experiments compared the recognition effects of graph convolutional networks， graph isomorphism networks， and GraphSAGE on the same dataset. The results show that the model outperforms the other models in accuracy， precision， and mean average precision， achieving 90.9%， 91.6%， and 91.9%， respectively. These results demonstrate the superiority of the model in capturing circuit connections， especially in terms of its effectiveness in processing complex circuit diagrams.

Key words: Key words: automated annotation, graph attention networks, circuit structure, feature extraction

中图分类号:

TP391

李鑫朋、仝明磊. 基于图注意力网络的模拟电路结构标注[J]. 计算机与现代化, 2025, 0(06): 101-105.

LI Xinpeng, TONG Minglei. Annotation of Analog Circuit Structures via Graph Attention Networks[J]. Computer and Modernization, 2025, 0(06): 101-105.

参考文献

［1］ LIN Y B， GAO X H， ZHANG H Y， et al. Intelligent and interactive analog layout design automation［C］// IEEE 16th International Conference on Solid-State & Integrated Circuit Technology （ICSICT）.IEEE， 2022:1-4.
［2］ HUANG G Y， HU J B， HE Y F， et al. Machine learning for electronic design automation: A survey［J］. ACM Transactions on Design Automation of Electronic Systems， 2021，5（26）:1-46.
［3］ LOPERA D S， SERVADEI L， KIPRIT G N， et al. A survey of graph neural networks for electronic design automation［C］// Then 3rd Workshop on Machine Learning for CAD （MLCAD）. ACM， 2021:1-6.
［4］ MASSIER T， GRAEB H， SCHLICHTMANN U. The sizing rules method for CMOS and bipolar analog integrated circuit synthesis［J］. IEEE Transactions on Computer-Aided Design， 2008，27（12）: 2209-2222.
［5］ MEISSNER M， HEDRIC L. FEATS: Framework for explorative analog topology synthesis［J］. IEEE Transactions on Computer-Aided Design， 2015，34（2）:213-226.
［6］ HARJANI R， RUTENBAR R.A， CARLEY L.R. A prototype framework for knowledge-based analog circuit synthesis［C］// 24th ACM/IEEE Design Automation Conference. ACM， 1987:42-49.
［7］ WU P H， LIN P H； CHEN T C， et al. A novel analog physical synthesis methodology integrating existent design expertise［J］. IEEE Transactions on Computer-Aided Design， 2015，34（2）:199-212.
［8］ SCARSELLI F， GORI M， TSOI A C， et al. The graph neural network model［J］. IEEE Transactions on Neural Networks， 2008，20（1）:61-80.
［9］ WU Z H， PAN S R， CHEN F W， et al. A comprehensive survey on graph neural networks［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021，32（1）:4-24.
［10］ WILLIAM L， HAMILTON， REX Y， et al. Representation learning on graphs: Methods and applications［J］. IEEE Data Engineering Bulletin， 2017，40:52-74.
［11］ XU B Y， ZHU K L， LIU M J， et al. MAGICAL: Toward fully automated analog IC layout leveraging human and machine intelligence［C］// 2019 International Conference on Computer-Aided Design （ICCAD）. ACM，2019:1-8.
［12］ HAMILTON W R， YING R， LESKOVEC J. Inductive representation learning on large graphs［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems（NeurIPS）. ACM， 2017:1024-1034.
［13］ KUNAL K， POOJARY J， DHAR T， et al. A general approach for identifying hierarchical symmetry constraints for analog circuit layout［C］// 2020 International Conference On Computer Aided Design （ICCAD）. ACM， 2020:1-8.
［14］ DEFFERRARD M， BRESSON X， VANDERGHEYNS P. Convolutional neural networks on graphs with fast localized spectral filtering［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems （NeurIPS）. ACM， 2016:3844-3852.
［15］ KIPF T N， WELLING M. Semi-supervised classification with graph convolutional networks［C］// International Conference on Learning Representations （ICLR）. ICLR， 2016:1-14.
［16］ LIOU G H， WANG S H， SU Y Y ，et al. Classifying analog and digital circuits with machine learning techniques toward mixed-signal design automation［C］// 2018 15th International Conference on Synthesis， Modeling， Analysis and Simulation Methods and Applications to Circuit Design （SMACD）. IEEE， 2018:173-176.
［17］ LI H， JIAO F S， DOBOLI A. Analog circuit topological feature extraction with unsupervised learning of new sub-structures［C］// 2016 Design， Automation & Test in Europe Conference & Exhibition. IEEE， 2016:1509-1512.
［18］ KUNAL K， TONMOY D， MEGHNA M， et al. GANA: Graph convolutional network based automated netlist annotation for analog circuits［C］// 2020 Design， Automation & Test in Europe Conference & Exhibition. IEEE， 2020:55-60.
［19］ KUNAL K， TONMOY D， MEGHNA M， et al. ALIGN: Open-source Analog Layout Automation from the ground up［C］// 2019 56th ACM/IEEE Design Automation Conference. IEEE， 2019:1-4.
［20］ LIU M J， LI W X， ZHU K R， et al. S3DET: Detecting system symmetry constraints for analog circuits with graph similarity［C］// 2020 25th Asia and South Pacific Design Automation Conference. IEEE， 2020:193-198.
［21］ CHEN H， ZHU K R， LIU M J， et al. Universal symmetry constraint extraction for analog and mixed-signal circuits with graph neural networks［C］// Design Automation Conference. ACM， 2021:1243-1248.
［22］ REN H X， KOKAI G F， TURNER W J， et al. ParaGraph: Layout parasitics and device parameter prediction using graph neural networks［C］// 2020 57th Design Automation Conference. ACM， 2020: 1-6.
［23］ GAO X H， DENG C H， LIU M J， et al. Layout symmetry annotation for analog circuits with graph neural networks［C］// 2021 26th Asia and South Pacific Design Automation Conference. IEEE， 2021:152-157.
［24］ YING R， H R N， et al. Graph convolutional neural networks for web-scale recommender systems［C］// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM， 2018:974-983.
［25］ LIU M J， ZHU K R， GU J Q， et al. Towards decrypting the art of analog layout， placement quality prediction via transfer learning［C］// 2020 Design， Automation & Test in Europe Conference & Exhibition. IEEE， 2020:496-501.
［26］ VELIČKOVIĆ P， CUCURULL G， CASANOVA A， et al. Graph attention networks［J］. arXiv preprint arXiv:1710.10
903， 2017.
［27］ LI Q， WANG D L， FENG S， et al. Global graph attention embedding network for relation prediction in knowledge graphs［J］. IEEE Transactions on Neural Networks and Learning Systems， 2022，33（11）:6712-6725.

[1]	刘子寒, 沈力, 奚梦婷, 朱佳佳, 陆佳鑫, 查俊杰. 基于虚拟化的数据中台资源隔离调度机制[J]. 计算机与现代化, 2025, 0(06): 120-126.
[2]	刘少君, 沙倚天, 金倩倩, 陈鹏, 吴越. 面向智能电网的LDA-IDF进程日志异常检测方法[J]. 计算机与现代化, 2025, 0(06): 114-119.
[3]	郭鑫溢1, 姜凯1, 杨朋威2, 陈更2. 基于深度强化学习的居民微电网调度算法[J]. 计算机与现代化, 2025, 0(06): 106-113.
[4]	张高义1, 徐杨1, 2, 曹斌1, 3, 李毅飞3. 基于数字孪生的铝电解槽三维可视化监控系统[J]. 计算机与现代化, 2024, 0(05): 104-109.
[5]	冯冼1, 2, 方昆1, 屈右铭1, 刘晓波1, 施佳驰1, 文立恒1. 气象服务中台关键技术研究与应用[J]. 计算机与现代化, 2024, 0(05): 69-74.
[6]	范良俊1, 彭振皖1, 王晨2, 于泓涛2, 梁振1. 基于YAML的iOS应用开发框架[J]. 计算机与现代化, 2024, 0(04): 115-120.
[7]	王鑫, 辛国江, 张杨, 朱磊. 基于Dilated ADU-Net的开放环境下的舌象分割算法#br#[J]. 计算机与现代化, 2024, 0(04): 48-54.
[8]	王晓霞, 孟佳娜, 江烽, 丁梓晴. 基于多视图的知识感知推荐系统#br#[J]. 计算机与现代化, 2024, 0(02): 100-107.
[9]	李诗月, 孟佳娜, 于玉海, 李雪莹, 许英傲. 基于知识增强的方面级情感分析方法[J]. 计算机与现代化, 2023, 0(10): 1-8.