{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:34:58Z","timestamp":1773246898260,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"General Research Fund of the Hong Kong Research Grants Council","award":["14212422"],"award-info":[{"award-number":["14212422"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676791","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T12:53:56Z","timestamp":1744203236000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["DeepGate3: Towards Scalable Circuit Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2186-9579","authenticated-orcid":false,"given":"Zhengyuan","family":"Shi","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Sha Tin, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6049-0457","authenticated-orcid":false,"given":"Ziyang","family":"Zheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Sha Tin, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1696-3429","authenticated-orcid":false,"given":"Sadaf","family":"Khan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Sha Tin, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9954-9563","authenticated-orcid":false,"given":"Jianyuan","family":"Zhong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Sha Tin, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5486-2947","authenticated-orcid":false,"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab, Huawei, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-126X","authenticated-orcid":false,"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Sha Tin, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"issue":"240","key":"e_1_3_2_1_1_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1--113, 2023.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023."},{"key":"e_1_3_2_1_3_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1--67","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1--67, 2020."},{"key":"e_1_3_2_1_4_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"e_1_3_2_1_6_1","volume-title":"Towards graph foundation models: A survey and beyond. arXiv preprint arXiv:2310.11829","author":"Liu Jiawei","year":"2023","unstructured":"Jiawei Liu, Cheng Yang, Zhiyuan Lu, Junze Chen, Yibo Li, Mengmei Zhang, Ting Bai, Yuan Fang, Lichao Sun, Philip S Yu, et al. Towards graph foundation models: A survey and beyond. arXiv preprint arXiv:2310.11829, 2023."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530497"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323798"},{"key":"e_1_3_2_1_9_1","volume-title":"Deepseq: Deep sequential circuit learning. arXiv preprint arXiv:2302.13608","author":"Khan Sadaf","year":"2023","unstructured":"Sadaf Khan, Zhengyuan Shi, Min Li, and Qiang Xu. Deepseq: Deep sequential circuit learning. arXiv preprint arXiv:2302.13608, 2023."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247828"},{"key":"e_1_3_2_1_11_1","volume-title":"Less is more: Hop-wise graph attention for scalable and generalizable learning on circuits. arXiv preprint arXiv:2403.01317","author":"Deng Chenhui","year":"2024","unstructured":"Chenhui Deng, Zichao Yue, Cunxi Yu, Gokce Sarar, Ryan Carey, Rajeev Jain, and Zhiru Zhang. Less is more: Hop-wise graph attention for scalable and generalizable learning on circuits. arXiv preprint arXiv:2403.01317, 2024."},{"key":"e_1_3_2_1_12_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020."},{"key":"e_1_3_2_1_13_1","volume-title":"Neural scaling laws on graphs. arXiv preprint arXiv:2402.02054","author":"Liu Jingzhe","year":"2024","unstructured":"Jingzhe Liu, Haitao Mao, Zhikai Chen, Tong Zhao, Neil Shah, and Jiliang Tang. Neural scaling laws on graphs. arXiv preprint arXiv:2402.02054, 2024."},{"key":"e_1_3_2_1_14_1","volume-title":"On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205","author":"Alon Uri","year":"2020","unstructured":"Uri Alon and Eran Yahav. On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205, 2020."},{"key":"e_1_3_2_1_15_1","volume-title":"Benjamin Paul Chamberlain, Xiaowen Dong, and Michael M Bronstein. Understanding over-squashing and bottlenecks on graphs via curvature. arXiv preprint arXiv:2111.14522","author":"Topping Jake","year":"2021","unstructured":"Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, and Michael M Bronstein. Understanding over-squashing and bottlenecks on graphs via curvature. arXiv preprint arXiv:2111.14522, 2021."},{"key":"e_1_3_2_1_16_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016."},{"key":"e_1_3_2_1_17_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems, 30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_18_1","volume-title":"How powerful are graph neural networks? arXiv preprint arXiv:1810.00826","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826, 2018."},{"key":"e_1_3_2_1_19_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_20_1","volume-title":"Sashank J Reddi, and Sanjiv Kumar. Are transformers universal approximators of sequence-to-sequence functions? arXiv preprint arXiv:1912.10077","author":"Yun Chulhee","year":"2019","unstructured":"Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J Reddi, and Sanjiv Kumar. Are transformers universal approximators of sequence-to-sequence functions? arXiv preprint arXiv:1912.10077, 2019."},{"key":"e_1_3_2_1_21_1","volume-title":"Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140","author":"Zhang Jiawei","year":"2020","unstructured":"Jiawei Zhang, Haopeng Zhang, Congying Xia, and Li Sun. Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140, 2020."},{"key":"e_1_3_2_1_22_1","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. Do transformers really perform badly for graph representation? NeurIPS, 34:28877--28888, 2021.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_23_1","volume-title":"Self-supervised graph transformer on large-scale molecular data. Advances in neural information processing systems, 33:12559--12571","author":"Rong Yu","year":"2020","unstructured":"Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, and Junzhou Huang. Self-supervised graph transformer on large-scale molecular data. Advances in neural information processing systems, 33:12559--12571, 2020."},{"key":"e_1_3_2_1_24_1","volume-title":"Opengraph: Towards open graph foundation models. arXiv preprint arXiv:2403.01121","author":"Xia Lianghao","year":"2024","unstructured":"Lianghao Xia, Ben Kao, and Chao Huang. Opengraph: Towards open graph foundation models. arXiv preprint arXiv:2403.01121, 2024."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITC50671.2022.00027"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10248001"},{"key":"e_1_3_2_1_27_1","volume-title":"Eda-driven preprocessing for sat solving. arXiv preprint arXiv:2403.19446","author":"Shi Zhengyuan","year":"2024","unstructured":"Zhengyuan Shi, Tiebing Tang, Sadaf Khan, Hui-Ling Zhen, Mingxuan Yuan, Zhufei Chu, and Qiang Xu. Eda-driven preprocessing for sat solving. arXiv preprint arXiv:2403.19446, 2024."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"e_1_3_2_1_29_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017."},{"key":"e_1_3_2_1_30_1","first-page":"5360","volume-title":"International Conference on Machine Learning","author":"Dong Zehao","year":"2022","unstructured":"Zehao Dong, Muhan Zhang, Fuhai Li, and Yixin Chen. Pace: A parallelizable computation encoder for directed acyclic graphs. In International Conference on Machine Learning, pages 5360--5377. PMLR, 2022."},{"key":"e_1_3_2_1_31_1","volume-title":"Practical graph isomorphism","author":"McKay Brendan D","year":"1981","unstructured":"Brendan D McKay et al. Practical graph isomorphism. 1981."},{"key":"e_1_3_2_1_32_1","volume-title":"Bert: Pretraining of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pretraining of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_33_1","volume-title":"On a relation between graph edit distance and maximum common subgraph. Pattern recognition letters, 18(8):689--694","author":"Bunke Horst","year":"1997","unstructured":"Horst Bunke. On a relation between graph edit distance and maximum common subgraph. Pattern recognition letters, 18(8):689--694, 1997."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"e_1_3_2_1_35_1","volume-title":"Sinong Wang, and Jie Tang. Blockwise self-attention for long document understanding. arXiv preprint arXiv:1911.02972","author":"Qiu Jiezhong","year":"2019","unstructured":"Jiezhong Qiu, Hao Ma, Omer Levy, Scott Wen-tau Yih, Sinong Wang, and Jie Tang. Blockwise self-attention for long document understanding. arXiv preprint arXiv:1911.02972, 2019."},{"key":"e_1_3_2_1_36_1","volume-title":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509, 2019."},{"key":"e_1_3_2_1_37_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150, 2020."},{"key":"e_1_3_2_1_38_1","volume-title":"Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198","author":"Liu Peter J","year":"2018","unstructured":"Peter J Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, and Noam Shazeer. Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198, 2018."},{"key":"e_1_3_2_1_39_1","unstructured":"Manzil Zaheer Guru Guruganesh Kumar Avinava Dubey Joshua Ainslie Chris Alberti Santiago Ontanon Philip Pham Anirudh Ravula Qifan Wang Li Yang et al. Big bird: Transformers for longer sequences. Advances in neural information processing systems 33:17283--17297 2020."},{"key":"e_1_3_2_1_40_1","volume-title":"ITSW","author":"Davidson Scott","year":"1999","unstructured":"Scott Davidson. Characteristics of the itc'99 benchmark circuits. In ITSW, 1999."},{"key":"e_1_3_2_1_41_1","volume-title":"IWLS","author":"Albrecht Christoph","year":"2005","unstructured":"Christoph Albrecht. Iwls 2005 benchmarks. In IWLS, 2005."},{"key":"e_1_3_2_1_42_1","volume-title":"IWLS, number CONF","author":"Amar\u00fa Luca","year":"2015","unstructured":"Luca Amar\u00fa, Pierre-Emmanuel Gaillardon, and Giovanni De Micheli. The epfl combinational benchmark suite. In IWLS, number CONF, 2015."},{"key":"e_1_3_2_1_43_1","unstructured":"Opencores Team. Opencores. https:\/\/opencores.org\/."},{"key":"e_1_3_2_1_44_1","volume-title":"Automation & Test in Europe Conference & Exhibition. IEEE","author":"Thakur Shailja","year":"2023","unstructured":"Shailja Thakur, Baleegh Ahmad, Zhenxing Fan, Hammond Pearce, Benjamin Tan, Ramesh Karri, Brendan Dolan-Gavitt, and Siddharth Garg. Benchmarking large language models for automated verilog rtl code generation. In 2023 Design, Automation & Test in Europe Conference & Exhibition. IEEE, 2023."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14295-6_5"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"e_1_3_2_1_47_1","first-page":"1466","volume-title":"International Conference on Machine Learning","author":"Bansal Yamini","year":"2022","unstructured":"Yamini Bansal, Behrooz Ghorbani, Ankush Garg, Biao Zhang, Colin Cherry, Behnam Neyshabur, and Orhan Firat. Data scaling laws in nmt: The effect of noise and architecture. In International Conference on Machine Learning, pages 1466--1482. PMLR, 2022."},{"key":"e_1_3_2_1_48_1","first-page":"36","article-title":"Scaling data-constrained language models","author":"Muennighoff Niklas","year":"2024","unstructured":"Niklas Muennighoff, Alexander Rush, Boaz Barak, Teven Le Scao, Nouamane Tazi, Aleksandra Piktus, Sampo Pyysalo, Thomas Wolf, and Colin A Raffel. Scaling data-constrained language models. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","first-page":"22300","article-title":"Revisiting neural scaling laws in language and vision","volume":"35","author":"Alabdulmohsin Ibrahim M","year":"2022","unstructured":"Ibrahim M Alabdulmohsin, Behnam Neyshabur, and Xiaohua Zhai. Revisiting neural scaling laws in language and vision. Advances in Neural Information Processing Systems, 35:22300--22312, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/800157.805047"},{"key":"e_1_3_2_1_51_1","first-page":"892","volume-title":"Automation and Test in Europe Conference and Exhibition","author":"Lu Feng","year":"2003","unstructured":"Feng Lu, L-C Wang, Kwang-Ting Cheng, and RC-Y Huang. A circuit sat solver with signal correlation guided learning. In 2003 Design, Automation and Test in Europe Conference and Exhibition, pages 892--897. IEEE, 2003."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213018400018"},{"key":"e_1_3_2_1_53_1","first-page":"9608","article-title":"Can q-learning with graph networks learn a generalizable branching heuristic for a sat solver?","volume":"33","author":"Kurin Vitaly","year":"2020","unstructured":"Vitaly Kurin, Saad Godil, Shimon Whiteson, and Bryan Catanzaro. Can q-learning with graph networks learn a generalizable branching heuristic for a sat solver? Advances in Neural Information Processing Systems, 33:9608--9621, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_54_1","volume-title":"2023 IEEE\/ACM International Conference on Computer Aided Design. IEEE","author":"Shi Zhengyuan","year":"2023","unstructured":"Zhengyuan Shi, Min Li, Yi Liu, Sadaf Khan, Junhua Huang, Hui-Ling Zhen, Mingxuan Yuan, and Qiang Xu. Satformer: Transformer-based unsat core learning. In 2023 IEEE\/ACM International Conference on Computer Aided Design. IEEE, 2023."},{"key":"e_1_3_2_1_55_1","first-page":"8","volume-title":"SAT RACE 2019","author":"SEPARATE DECISION","year":"2019","unstructured":"SEPARATE DECISION QUEUE. Cadical at the sat race 2019. SAT RACE 2019, page 8, 2019."}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676791","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:44Z","timestamp":1750295924000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676791"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":55,"alternative-id":["10.1145\/3676536.3676791","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676791","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}