{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:31Z","timestamp":1750219771054,"version":"3.41.0"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T00:00:00Z","timestamp":1676505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272467 and U2001212"],"award-info":[{"award-number":["62272467 and U2001212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Outstanding Young Scientist Program","award":["BJJWZYJH012019100020098"],"award-info":[{"award-number":["BJJWZYJH012019100020098"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2023,4,30]]},"abstract":"<jats:p>Deep semantic matching aims at discriminating the relationship between documents based on deep neural networks. In recent years, it becomes increasingly popular to organize documents with a graph structure, then leverage both the intrinsic document features and the extrinsic neighbor features to derive discrimination. Most of the existing works mainly care about how to utilize the presented neighbors, whereas limited effort is made to filter appropriate neighbors. We argue that the neighbor features could be highly noisy and partially useful. Thus, a lack of effective neighbor selection will not only incur a great deal of unnecessary computation cost but also restrict the matching accuracy severely.<\/jats:p>\n          <jats:p>\n            In this work, we propose a novel framework,\n            <jats:bold>C<\/jats:bold>\n            ascaded\n            <jats:bold>D<\/jats:bold>\n            eep\n            <jats:bold>S<\/jats:bold>\n            emantic\n            <jats:bold>M<\/jats:bold>\n            atching (\n            <jats:bold>CDSM<\/jats:bold>\n            ), for accurate and efficient semantic matching on textual graphs. CDSM is highlighted for its two-stage workflow. In the first stage, a lightweight CNN-based ad-hod neighbor selector is deployed to filter useful neighbors for the matching task with a small computation cost. We design both one-step and multi-step selection methods. In the second stage, a high-capacity graph-based matching network is employed to compute fine-grained relevance scores based on the well-selected neighbors. It is worth noting that CDSM is a generic framework which accommodates most of the mainstream graph-based semantic matching networks. The major challenge is how the selector can learn to discriminate the neighbors\u2019 usefulness which has no explicit labels. To cope with this problem, we design a weak-supervision strategy for optimization, where we train the graph-based matching network at first and then the ad-hoc neighbor selector is learned on top of the annotations from the matching network. We conduct extensive experiments with three large-scale datasets, showing that CDSM notably improves the semantic matching accuracy and efficiency thanks to the selection of high-quality neighbors. The source code is released at https:\/\/github.com\/jingjyyao\/CDSM.\n          <\/jats:p>","DOI":"10.1145\/3573204","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T13:45:03Z","timestamp":1669988703000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["CDSM:\n            <u>C<\/u>\n            ascaded\n            <u>D<\/u>\n            eep\n            <u>S<\/u>\n            emantic\n            <u>M<\/u>\n            atching on Textual Graphs Leveraging Ad-hoc Neighbor Selection"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0527-6095","authenticated-orcid":false,"given":"Jing","family":"Yao","sequence":"first","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3437-2630","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0826-4524","authenticated-orcid":false,"given":"Junhan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-948X","authenticated-orcid":false,"given":"Zhicheng","family":"Dou","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8608-8482","authenticated-orcid":false,"given":"Xing","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Key Laboratory of Data Engineering and Knowledge Engineering, MOE, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"unstructured":"Siddhant Arora. 2020. A survey on graph neural networks for knowledge graph completion. arXiv:2007.12374. Retrieved from https:\/\/arxiv.org\/abs\/2007.12374.","key":"e_1_3_2_2_2"},{"key":"e_1_3_2_3_2","first-page":"642","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Bao Hangbo","year":"2020","unstructured":"Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Jianfeng Gao, Songhao Piao, Ming Zhou, and Hsiao-Wuen Hon. 2020. UniLMv2: Pseudo-masked language models for unified language model pre-training. In Proceedings of the 37th International Conference on Machine Learning. PMLR, 642\u2013652."},{"doi-asserted-by":"publisher","key":"e_1_3_2_4_2","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_2_5_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 4171\u20134186."},{"doi-asserted-by":"publisher","key":"e_1_3_2_6_2","DOI":"10.1145\/2983323.2983769"},{"doi-asserted-by":"publisher","key":"e_1_3_2_7_2","DOI":"10.5555\/3294771.3294869"},{"key":"e_1_3_2_8_2","first-page":"1024","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 1024\u20131034."},{"doi-asserted-by":"publisher","key":"e_1_3_2_9_2","DOI":"10.18653\/v1\/2020.acl-main.392"},{"doi-asserted-by":"publisher","key":"e_1_3_2_10_2","DOI":"10.1145\/2505515.2505665"},{"doi-asserted-by":"publisher","key":"e_1_3_2_11_2","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"doi-asserted-by":"publisher","key":"e_1_3_2_12_2","DOI":"10.1145\/3397271.3401075"},{"doi-asserted-by":"publisher","key":"e_1_3_2_13_2","DOI":"10.1080\/01638539809545028"},{"doi-asserted-by":"publisher","key":"e_1_3_2_14_2","DOI":"10.1145\/3404835.3462926"},{"unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv:1907.11692. Retrieved from https:\/\/arxiv.org\/abs\/1907.11692.","key":"e_1_3_2_15_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_16_2","DOI":"10.1162\/tacl_a_00369"},{"doi-asserted-by":"publisher","key":"e_1_3_2_17_2","DOI":"10.1109\/TASLP.2016.2520371"},{"doi-asserted-by":"publisher","key":"e_1_3_2_18_2","DOI":"10.18653\/v1\/D19-1410"},{"doi-asserted-by":"publisher","key":"e_1_3_2_19_2","DOI":"10.5555\/1823431"},{"key":"e_1_3_2_20_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Seo Min Joon","year":"2017","unstructured":"Min Joon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2017. Bidirectional attention flow for machine comprehension. In Proceedings of the 5th International Conference on Learning Representations. OpenReview.net."},{"doi-asserted-by":"publisher","key":"e_1_3_2_21_2","DOI":"10.1145\/2567948.2577348"},{"key":"e_1_3_2_22_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations. OpenReview.net."},{"doi-asserted-by":"publisher","key":"e_1_3_2_23_2","DOI":"10.1145\/3219819.3219869"},{"doi-asserted-by":"publisher","key":"e_1_3_2_24_2","DOI":"10.3390\/sym13030485"},{"doi-asserted-by":"publisher","key":"e_1_3_2_25_2","DOI":"10.1162\/tacl_a_00360"},{"unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey Jeff Klingner Apurva Shah Melvin Johnson Xiaobing Liu Lukasz Kaiser Stephan Gouws Yoshikiyo Kato Taku Kudo Hideto Kazawa Keith Stevens George Kurian Nishant Patil Wei Wang Cliff Young Jason Smith Jason Riesa Alex Rudnick Oriol Vinyals Greg Corrado Macduff Hughes and Jeffrey Dean. 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv:1609.08144. Retrieved from https:\/\/arxiv.org\/abs\/1609.08144.","key":"e_1_3_2_26_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_27_2","DOI":"10.1145\/3209978.3210181"},{"key":"e_1_3_2_28_2","article-title":"GraphFormers: GNN-nested transformers for representation learning on textual graph","author":"Yang Junhan","year":"2021","unstructured":"Junhan Yang, Zheng Liu, Shitao Xiao, Chaozhuo Li, Defu Lian, Sanjay Agrawal, S. Amit, Guangzhong Sun, and Xing Xie. 2021. GraphFormers: GNN-nested transformers for representation learning on textual graph. In Proceedings of the 35th Conference on Neural Information Processing Systems.","journal-title":"In Proceedings of the 35th Conference on Neural Information Processing Systems."},{"doi-asserted-by":"publisher","key":"e_1_3_2_29_2","DOI":"10.18653\/v1\/N16-1174"},{"doi-asserted-by":"publisher","key":"e_1_3_2_30_2","DOI":"10.1145\/3397271.3401153"},{"doi-asserted-by":"publisher","key":"e_1_3_2_31_2","DOI":"10.1145\/3219819.3219890"},{"doi-asserted-by":"publisher","key":"e_1_3_2_32_2","DOI":"10.1145\/3442381.3449865"},{"doi-asserted-by":"publisher","key":"e_1_3_2_33_2","DOI":"10.1145\/3442381.3449842"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573204","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:25Z","timestamp":1750178245000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,16]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,4,30]]}},"alternative-id":["10.1145\/3573204"],"URL":"https:\/\/doi.org\/10.1145\/3573204","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2023,2,16]]},"assertion":[{"value":"2021-11-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-07","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}