{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:51:04Z","timestamp":1773931864618,"version":"3.50.1"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"Proof of Concept Foundation of Xidian University Hangzhou Institute of Technology","award":["GNYZ2024GY005"],"award-info":[{"award-number":["GNYZ2024GY005"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62404161"],"award-info":[{"award-number":["62404161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["YJSJ25013"],"award-info":[{"award-number":["YJSJ25013"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"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>This article proposes a method to generate accurate and concise analytic equations for device compact modeling using Physics-Assisted Kolmogorov\u2013Arnold Networks (PKAN). The equations are directly extracted from the trained neural network architecture. PKAN uses variable activation functions informed by prior physical knowledge to model device behaviors. Similarity constraints map these trained activation functions to mathematical symbols. Sparsification techniques simplify the network structure, producing concise and explicit equations. This article also presents four approaches for physics-assisted device modeling using PKAN: (1) generating entire continuous equations without human intervention, (2) applying correlation factors to existing models without requiring knowledge of internal physical mechanisms, (3) revising specific parts of existing models, and (4) automatically extending existing models. Experimental results show that PKAN demonstrates significant accuracy improvements, achieving error reductions of 91.8%, 91.5%, 66.2%, and 83.7% for corresponding experiments, respectively. These findings demonstrate PKAN\u2019s potential for various device modeling applications. By combining the precision of neural networks with the clarity of symbolic representation, PKAN offers a powerful tool for device modeling applications.<\/jats:p>","DOI":"10.1145\/3765904","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T11:05:29Z","timestamp":1758798329000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Accurate Analytic Equation Generation for Compact Modeling with Physics-Assisted Kolmogorov-Arnold Networks"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9033-2129","authenticated-orcid":false,"given":"Guangxin","family":"Guo","sequence":"first","affiliation":[{"name":"Xidian University School of Microelectronics","place":["Xi'an, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5236-9745","authenticated-orcid":false,"given":"Zhengguang","family":"Tang","sequence":"additional","affiliation":[{"name":"Xidian University School of Microelectronics","place":["Xi'an, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2307-5332","authenticated-orcid":false,"given":"Zhenhai","family":"Cui","sequence":"additional","affiliation":[{"name":"Xidian University School of Microelectronics","place":["Xi'an, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6289-6680","authenticated-orcid":false,"given":"Cong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xidian University","place":["Xian, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-3780","authenticated-orcid":false,"given":"Handing","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University School of Artificial Intelligence","place":["Xi'an, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3427-5320","authenticated-orcid":false,"given":"Hailong","family":"You","sequence":"additional","affiliation":[{"name":"Xidian University School of Microelectronics","place":["Xi'an, China"]}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"2020. BSIM4 4.8.2. (2020). Retrieved from https:\/\/bsim.berkeley.edu\/models\/bsim4\/"},{"key":"e_1_3_2_3_2","unstructured":"2022. BSIM-CMG 111.2.0. (2022). Retrieved from http:\/\/bsim.berkeley.edu\/models\/bsimcmg\/"},{"key":"e_1_3_2_4_2","volume-title":"NGSPICE","year":"2025","unstructured":"2025. NGSPICE. Retrieved from https:\/\/sourceforge.net\/projects\/ngspiceAccessed: 2025-08-20."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/JEDS.2015.2415584"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2005.881006"},{"key":"e_1_3_2_7_2","volume-title":"Neural Networks: A Comprehensive Foundation (2nd edn)","author":"Haykin Simon","year":"1998","unstructured":"Simon Haykin. 1998. Neural Networks: A Comprehensive Foundation (2nd edn). Prentice Hall PTR, USA."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3698195"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/JEDS.2023.3246477"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/LED.2022.3168243"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/LED.2022.3168243"},{"key":"e_1_3_2_12_2","unstructured":"Keysight Technologies. 2024. PathWave Model Builder (MBP). (2024). Retrieved from https:\/\/www.keysight.com"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474364"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/JXCDC.2016.2636161"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fmre.2024.01.010"},{"key":"e_1_3_2_16_2","unstructured":"Ziming Liu Yixuan Wang Sachin Vaidya Fabian Ruehle James Halverson Marin Solja\u010di\u0107 Thomas Y. Hou and Max Tegmark. 2024. KAN: Kolmogorov-Arnold Networks. arXiv:2404.19756. Retrieved from https:\/\/arxiv.org\/abs\/\/2404.19756"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/LED.2020.3045064"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICEES61253.2024.10776832"},{"key":"e_1_3_2_19_2","unstructured":"PyTorch Developers. 2025. torch.optim.Adam \u2013 PyTorch documentation. (2025). Retrieved from https:\/\/docs.pytorch.org\/docs\/stable\/generated\/torch.optim.Adam.html#torch.optim.AdamAccessed: 2025-06-04."},{"key":"e_1_3_2_20_2","unstructured":"PyTorch Developers. 2025. torch.optim.LBFGS \u2013 PyTorch documentation. (2025). Retrieved from https:\/\/pytorch.org\/docs\/stable\/generated\/torch.optim.LBFGS.htmlAccessed: 2025-06-04."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3440014"},{"key":"e_1_3_2_22_2","volume-title":"PrimeSim\u2122 MOSRA User Guide","year":"2021","unstructured":"Synopsys. 2021. PrimeSim\u2122 MOSRA User Guide. Retrieved from https:\/\/www.synopsys.comAccessed: 2023-09-20."},{"key":"e_1_3_2_23_2","volume-title":"PrimeSim\u2122 HSPICE","year":"2025","unstructured":"Synopsys. 2025. PrimeSim\u2122 HSPICE. Retrieved from https:\/\/www.synopsys.comAccessed: 2025-08-20."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2025.3556049"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSICT.2010.5667399"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2023.3244901"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/SISPAD62626.2024.10733248"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aay2631"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2020.3048918"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISEDA62518.2024.10617534"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11172761"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2022.3175708"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2021.3093376"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2023.3269410"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2018.2843681"},{"key":"e_1_3_2_36_2","unstructured":"Zhenghao Zhou Yiyan Li Zelin Guo Zheng Yan and Mo-Yuen Chow. 2024. A white-box deep-learning method for electrical energy system modeling based on Kolmogorov-Arnold Network. arXiv:2409.08044. Retrieved from https:\/\/arxiv.org\/abs\/\/2409.08044"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T12:16:35Z","timestamp":1773922595000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765904"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3765904"],"URL":"https:\/\/doi.org\/10.1145\/3765904","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"2025-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}