Graph Neural Networks Based Analog Circuit Link Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Guanyuan, Zhou, Tiansheng, Zhao, Jianxiang, Li, Zhi, Lin, Yugui, Ma, Bingtao, Wang, Yaqi, Liò, Pietro, Wang, Shuai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918207633227776
author Pan, Guanyuan
Zhou, Tiansheng
Zhao, Jianxiang
Li, Zhi
Lin, Yugui
Ma, Bingtao
Wang, Yaqi
Liò, Pietro
Wang, Shuai
author_facet Pan, Guanyuan
Zhou, Tiansheng
Zhao, Jianxiang
Li, Zhi
Lin, Yugui
Ma, Bingtao
Wang, Yaqi
Liò, Pietro
Wang, Shuai
contents Circuit link prediction, which identifies missing component connections from incomplete netlists, is crucial in analog circuit design automation. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats restricts model flexibility. We propose Graph Neural Networks Based Analog Circuit Link Prediction (GNN-ACLP), a graph neural networks (GNNs) based method featuring three innovations to tackle these challenges. First, we introduce the SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool that leverages retrieval-augmented generation (RAG) with a large language model (LLM) to enhance the compatibility of netlist formats. Finally, we build a comprehensive dataset, SpiceNetlist, comprising 775 annotated circuits of 7 different types across 10 component classes. Experiments demonstrate accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI compared to the baseline in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, demonstrating robust feature transfer capabilities. However, its linear computational complexity makes processing large-scale netlists challenging and requires future addressing.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10240
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph Neural Networks Based Analog Circuit Link Prediction
Pan, Guanyuan
Zhou, Tiansheng
Zhao, Jianxiang
Li, Zhi
Lin, Yugui
Ma, Bingtao
Wang, Yaqi
Liò, Pietro
Wang, Shuai
Hardware Architecture
Machine Learning
Circuit link prediction, which identifies missing component connections from incomplete netlists, is crucial in analog circuit design automation. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats restricts model flexibility. We propose Graph Neural Networks Based Analog Circuit Link Prediction (GNN-ACLP), a graph neural networks (GNNs) based method featuring three innovations to tackle these challenges. First, we introduce the SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool that leverages retrieval-augmented generation (RAG) with a large language model (LLM) to enhance the compatibility of netlist formats. Finally, we build a comprehensive dataset, SpiceNetlist, comprising 775 annotated circuits of 7 different types across 10 component classes. Experiments demonstrate accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI compared to the baseline in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, demonstrating robust feature transfer capabilities. However, its linear computational complexity makes processing large-scale netlists challenging and requires future addressing.
title Graph Neural Networks Based Analog Circuit Link Prediction
topic Hardware Architecture
Machine Learning
url https://arxiv.org/abs/2504.10240