• Home
  • Search
  • Accelerating Transistor Simulations with Self-Supervised Graph Attention Networks
  • https://doi.org/10.1109/access.2026.3675354Copy DOI Icon

Accelerating Transistor Simulations with Self-Supervised Graph Attention Networks

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Technology CAD (TCAD) tools are pivotal for transistor modeling, enabling physics-based simulations with high accuracy essential for developing next-generation technology nodes. However, their high computational cost and low throughput severely constrain large-scale design-space exploration. Accelerating TCAD simulations while preserving physical accuracy has therefore become a central research objective. A promising approach involves the use of graph-based representations of TCAD meshes fed into graph neural networks (GNNs), which offer rapid and accurate alternatives. However, traditional GNNs, such as Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) often falter with noisy transistor-mesh graphs, where embeddings become cluttered and complex. In thiswork, we propose a self-supervisedGNNframework for TCAD device modeling, specifically employing the Self-Supervised GAT (SuperGAT).We demonstrate that self-supervised GNN models, in contrast to GCNs and GATs, introduces a self-supervised edge-prediction task to distinguish informative from redundant topological connections. Our evaluation compares various GNN aggregation schemes demonstrates that SuperGAT successfully reproduces key transistor transfer characteristics drain current–gate voltage (Id–Vg) curves, subthreshold swing (SS) and threshold voltage (Vth). The dataset was generated using 14nm FDSOI transistors. Our SuperGAT model achieves a minimum <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 0.992 across all characteristics and an inference time of only 0.007 134 sec per transistor, resulting in a speed-up exceeding 100 000 x compared to TCAD simulation, which underscore the capability to substantially accelerate TCAD transistor simulations in advanced technology development.

Similar Papers
  • Research Article
  • Citations21

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

  • Jun 09, 2023
  • Expert Systems with Applications
  • Ruiqin Wang +2
  • Conference Article
  • Citations321

Exploiting Edge Features for Graph Neural Networks

  • Jun 01, 2019
  • Liyu Gong +1
  • Supplementary Content

Network-Integrated Reverse Vaccinology Using Biomni-Prioritized Features and Graph Neural Networks in Flavobacterium

  • Nov 14, 2025
  • Research Square
  • Muhammad Zafarullah Kazim +5
  • Research Article
  • Citations27

Improved GNNs for Log D7.4 Prediction by Transferring Knowledge from Low-Fidelity Data

  • Mar 31, 2023
  • Journal of Chemical Information and Modeling
  • Yan-Jing Duan +10
  • Conference Article
  • Citations84

Graph Neural Network (GNN) in Image and Video Understanding Using Deep Learning for Computer Vision Applications

  • Aug 04, 2021
  • P Pradhyumna +2
  • Research Article
  • Citations2

AI-Driven molecule generation and bioactivity prediction: A multi-model approach combining VAE, graph and language-based neural networks.

  • Dec 01, 2025
  • Computational biology and chemistry
  • Latefa Oulladji +4
  • Research Article
  • Citations12

A review of challenges and solutions in the design and implementation of deep graph neural networks

  • Oct 18, 2022
  • International Journal of Computers and Applications
  • Aafaq Mohi Ud Din +1
  • Conference Article
  • Citations7

Knowledge Enhanced Graph Neural Networks

  • Oct 09, 2023
  • Luisa Werner +3
  • Conference Article

Machine Learning Approach to Predict Tunnel FET Characteristics Using Random Forest Regression

  • Jan 08, 2026
  • Ajaykumar Dharmireddy +5
  • Research Article
  • Citations3

Improving drug-induced liver injury prediction using graph neural networks with augmented graph features from molecular optimisation

  • Aug 18, 2025
  • Journal of Cheminformatics
  • Taeyeub Lee +1
  • Research Article
  • Citations6

A U-Net Enhanced Graph Neural Network to Simulate Geological Carbon Sequestration

  • May 15, 2025
  • SPE Journal
  • Zeeshan Tariq +6
  • Research Article

Natural Language Processing (NLP): A Comparative Study on Applications of GNNs for the Tasks Like Text Classification, Semantic Role Labelling, and Abstract Meaning Representation Parsing

  • Jan 05, 2026
  • International Journal of Science and Research (IJSR)
  • Pathan Ashhad Zakirkhan +1
  • Research Article

Harnessing Graph Neural Networks (Gnn) For Automated Test Case Prioritization: Challenges and Opportunities in Qa Automation

  • Apr 03, 2025
  • The American Journal of Engineering and Technology
  • Anatolii Husakovskyi
  • Research Article
  • Citations10

Graph-CAT: Graph Co-Attention Networks via local and global attribute augmentations

  • Jan 04, 2021
  • Future Generation Computer Systems
  • Liang Yang +3
  • Research Article
  • Citations57

A new ensemble deep graph reinforcement learning network for spatio-temporal traffic volume forecasting in a freeway network

  • Jan 29, 2022
  • Digital Signal Processing
  • Pan Shang +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.