{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T11:18:32Z","timestamp":1774005512587,"version":"3.50.1"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:p>Unlike circuit parameter and sizing optimizations, the automated design of analog circuit topologies poses significant challenges for learning-based approaches. One challenge arises from the combinatorial growth of the topology space with circuit size, which limits the topology optimization efficiency. Moreover, traditional circuit evaluation methods are time-consuming, while the presence of data discontinuity in the topology space makes the accurate prediction of circuit performance exceptionally difficult for unseen topologies. To tackle these challenges, we design a novel Graph-Transformer-based Network (GTN) as the surrogate model for circuit evaluation, offering a substantial acceleration in the speed of circuit topology optimization without sacrificing performance. Our GTN model architecture is designed to embed voltage changes in circuit loops and current flows in connected devices, enabling accurate performance predictions for circuits with unseen topologies. To address the cold start problem when scaling GTN to large-scale circuits, we further introduce a curriculum learning strategy that progressively trains GTN from small-scale to large-scale circuits. This approach enables the model to first learn fundamental physical principles from simpler topologies and gradually adapt to complex configurations, effectively bridging the circuit complexity gap and improving prediction accuracy. Taking the power converter circuit design as an experimental task, our GTN model significantly outperforms an analytical approach and baseline methods directly utilizing graph neural networks. Furthermore, GTN achieves less than 5% relative error and 196\u00d7 speed-up compared with high-fidelity simulation. Notably, our GTN surrogate model empowers an automatic circuit design framework to discover circuits of comparable quality to those identified through high-fidelity simulation while reducing the time required by up to 98.2%. With curriculum learning, the enhanced GTN achieves a 51% improvement for performance prediction of large-scale circuits compared to the GTN model without this strategy. These advancements establish GTN as a scalable framework for automated analog circuit design across varying circuit complexity levels.<\/jats:p>","DOI":"10.1145\/3768167","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T10:35:01Z","timestamp":1758105301000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Generalizable and Efficient Circuit Topology Design: A Graph-Transformer-based Surrogate Model with Curriculum Learning"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6057-1832","authenticated-orcid":false,"given":"Haoshu","family":"Lu","sequence":"first","affiliation":[{"name":"New Jersey Institute of Technology","place":["Newark, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3496-6076","authenticated-orcid":false,"given":"Shaoze","family":"Fan","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology","place":["Newark, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5046-6579","authenticated-orcid":false,"given":"Shun","family":"Zhang","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab","place":["Cambridge, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-1051","authenticated-orcid":false,"given":"Ningyuan","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Notre Dame","place":["Notre Dame, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0579-2268","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"IBM Research","place":["Yorktown Heights, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6865-7290","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Science, New Jersey Institute of Technology","place":["Newark, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3110807"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3194267"},{"key":"e_1_3_1_5_2","unstructured":"C. Chang Y. Shen S. Fan J. Li S. Zhang N. Cao Y. Chen and X. Zhang. 2024. Lamagic: Language-model-based topology generation for analog integrated circuits. arXiv:2407.18269. Retrieved from https:\/\/arxiv.org\/abs\/2407.18269"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586211"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3107250"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116544"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643552"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656258"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942062"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643581"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586239"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/3118790.3119280"},{"key":"e_1_3_1_15_2","unstructured":"T. Kipf and M. Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. Retrieved from https:\/\/arxiv.org\/abs\/1609.02907"},{"key":"e_1_3_1_16_2","unstructured":"M. Kumar B. Packer and D. Koller. 2010. Self-paced learning for latent variable models. Advances in Neural Information Processing Systems 23 (2010) 1189\u20131197."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116329"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415624"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3416894"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218582"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2010.2093581"},{"key":"e_1_3_1_23_2","unstructured":"H. Vogt G. Atkinson and P. Nenzi. 2011. Ngspice User\u2019s Manual Version 44 2024. Available at https:\/\/ngspice.sourceforge.io\/docs.html"},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","unstructured":"E. Platanios O. Stretcu G. Neubig B. Poczos and T. Mitchell. 2019. Competence-based curriculum learning for neural machine translation. arXiv:1903.09848. Retrieved from https:\/\/arxiv.org\/abs\/1903.09848","DOI":"10.18653\/v1\/N19-1119"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/PESC.1980.7089440"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218515"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218495"},{"key":"e_1_3_1_28_2","unstructured":"A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A. N. Gomez \u0141. Kaiser and I. Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017) 6000\u20136010."},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218757"},{"issue":"9","key":"e_1_3_1_30_2","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang X.","year":"2022","unstructured":"X. Wang, Y. Chen, and W. Zhu. 2022. A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2022), 4555\u20134576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431562"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045574"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3221694"},{"key":"e_1_3_1_34_2","first-page":"7364","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zhang G.","year":"2019","unstructured":"G. Zhang, H. He, and D. Katabi. 2019. Circuit-GNN: Graph neural networks for distributed circuit design. In Proceedings of the International Conference on Machine Learning. PMLR, 7364\u20137373."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218643"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2977605"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415714"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3768167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:12:07Z","timestamp":1773997927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3768167"],"URL":"https:\/\/doi.org\/10.1145\/3768167","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"assertion":[{"value":"2025-03-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}