{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:11Z","timestamp":1755794891401,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Iflytek joint research program"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62337001,62477044"],"award-info":[{"award-number":["62337001,62477044"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Technologies R & D Program of Anhui Province","award":["202423k09020039"],"award-info":[{"award-number":["202423k09020039"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709263","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"695-706","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MGS3: A Multi-Granularity Self-Supervised Code Search Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3657-1133","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3898-0176","authenticated-orcid":false,"given":"Junfeng","family":"Kang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1609-0747","authenticated-orcid":false,"given":"Liyang","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8689-0763","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9147-9604","authenticated-orcid":false,"given":"Yunhao","family":"Sha","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6036-5095","authenticated-orcid":false,"given":"Linbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1661-0420","authenticated-orcid":false,"given":"Zhenya","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.449"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJOFETxR-","author":"Allamanis Miltiadis","year":"2018","unstructured":"Miltiadis Allamanis, Marc Brockschmidt, and Mahmoud Khademi. 2018. Learning to Represent Programs with Graphs. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJOFETxR-"},{"key":"e_1_3_2_2_3_1","volume-title":"International Conference on Learning Representations.","author":"Alon Uri","year":"2018","unstructured":"Uri Alon, Shaked Brody, Omer Levy, and Eran Yahav. 2018. code2seq: Generating Sequences from Structured Representations of Code. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462840"},{"key":"e_1_3_2_2_5_1","first-page":"20421","article-title":"Pyramid Attention For Source Code Summarization","volume":"35","author":"Chai Lei","year":"2022","unstructured":"Lei Chai and Ming Li. 2022. Pyramid Attention For Source Code Summarization. Advances in Neural Information Processing Systems, Vol. 35 (2022), 20421--20433.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_6_1","unstructured":"Yangruibo Ding Luca Buratti Saikat Chakraborty Saurabh Pujar Alessandro Morari and Baishakhi Ray. 2021. Contrastive learning for source code with structural and functional properties. (2021)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139nolinkurl10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_2_2_9_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In 9th International Conference on Learning Representations, ICLR 2021","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin B. Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. https:\/\/openreview.net\/forum?id=jLoC4ez43PZ"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559757"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681496"},{"key":"e_1_3_2_2_13_1","volume-title":"Neural code search revisited: Enhancing code snippet retrieval through natural language intent. arXiv preprint arXiv:2008.12193","author":"Heyman Geert","year":"2020","unstructured":"Geert Heyman and Tom Van Cutsem. 2020. Neural code search revisited: Enhancing code snippet retrieval through natural language intent. arXiv preprint arXiv:2008.12193 (2020)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196321.3196334"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09730-9"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"David A Hull. 1999. Xerox TREC-8 Question Answering Track Report.. In TREC.","DOI":"10.6028\/NIST.SP.500-246.xerox"},{"key":"e_1_3_2_2_18_1","volume-title":"Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436","author":"Husain Hamel","year":"2019","unstructured":"Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt. 2019. Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436 (2019)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1195"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.482"},{"key":"e_1_3_2_2_21_1","volume-title":"Learning and Evaluating Contextual Embedding of Source Code. In International Conference on Machine Learning. 5110--5121","author":"Kanade Aditya","year":"2020","unstructured":"Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi. 2020. Learning and Evaluating Contextual Embedding of Source Code. In International Conference on Machine Learning. 5110--5121."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389268"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.327"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.786"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40029-1"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28713"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.123"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.187"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2924374"},{"key":"e_1_3_2_2_31_1","volume-title":"Fixing Weight Decay Regularization in Adam. CoRR","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Fixing Weight Decay Regularization in Adam. CoRR, Vol. abs\/1711.05101 (2017). showeprint[arXiv]1711.05101 http:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_2_2_32_1","volume-title":"Shengyu Fu, and Shujie Liu.","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin B. Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, Ming Gong, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, and Shujie Liu. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation."},{"key":"e_1_3_2_2_33_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the first instructional conference on machine learning","volume":"242","author":"Juan","unstructured":"Juan Ramos et al. 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, Vol. 242. Citeseer, 29--48."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.332"},{"key":"e_1_3_2_2_38_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey E. Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9 (2008), 2579--2605. https:\/\/api.semanticscholar.org\/CorpusID:5855042","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3201037"},{"key":"e_1_3_2_2_40_1","volume-title":"Syncobert: Syntax-guided multi-modal contrastive pre-training for code representation. arXiv preprint arXiv:2108.04556","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yasheng Wang, Fei Mi, Pingyi Zhou, Yao Wan, Xiao Liu, Li Li, Hao Wu, Jin Liu, and Xin Jiang. 2021. Syncobert: Syntax-guided multi-modal contrastive pre-training for code representation. arXiv preprint arXiv:2108.04556 (2021)."},{"key":"e_1_3_2_2_41_1","volume-title":"Nghi DQ Bui, Junnan Li, and Steven CH Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi DQ Bui, Junnan Li, and Steven CH Hoi. 2023. Codet5: Open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922 (2023)."},{"key":"e_1_3_2_2_42_1","volume-title":"Code generation as a dual task of code summarization. Advances in neural information processing systems","author":"Wei Bolin","year":"2019","unstructured":"Bolin Wei, Ge Li, Xin Xia, Zhiyi Fu, and Zhi Jin. 2019. Code generation as a dual task of code summarization. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_43_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations.","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186081"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196408"},{"key":"e_1_3_2_2_46_1","volume-title":"Adversarial Retriever-Ranker for Dense Text Retrieval. In International Conference on Learning Representations.","author":"Zhang Hang","year":"2021","unstructured":"Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan, and Weizhu Chen. 2021. Adversarial Retriever-Ranker for Dense Text Retrieval. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_47_1","volume-title":"Implant Global and Local Hierarchy Information to Sequence based Code Representation Models. arXiv preprint arXiv:2303.07826","author":"Zhang Kechi","year":"2023","unstructured":"Kechi Zhang, Zhuo Li, Zhi Jin, and Ge Li. 2023. Implant Global and Local Hierarchy Information to Sequence based Code Representation Models. arXiv preprint arXiv:2303.07826 (2023)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645369"},{"volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Zhang Zheng","key":"e_1_3_2_2_49_1","unstructured":"Zheng Zhang, Qi Liu, Hao Jiang, Fei Wang, Yan Zhuang, Le Wu, Weibo Gao, and Enhong Chen. [n.,d.]. Fairlisa: Fair user modeling with limited sensitive attributes information. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2023.1274"},{"key":"e_1_3_2_2_51_1","volume-title":"Xlcost: A benchmark dataset for cross-lingual code intelligence. arXiv preprint arXiv:2206.08474","author":"Zhu Ming","year":"2022","unstructured":"Ming Zhu, Aneesh Jain, Karthik Suresh, Roshan Ravindran, Sindhu Tipirneni, and Chandan K Reddy. 2022. Xlcost: A benchmark dataset for cross-lingual code intelligence. arXiv preprint arXiv:2206.08474 (2022)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709263","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:44:03Z","timestamp":1755359043000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":51,"alternative-id":["10.1145\/3690624.3709263","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709263","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}