{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:10:39Z","timestamp":1763536239029,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Research Foundation, Singapore, and the Cyber Security Agency under its National Cybersecurity R&D Programme","award":["NCRP25-P04-TAICeN"],"award-info":[{"award-number":["NCRP25-P04-TAICeN"]}]},{"name":"NRF Investigatorship","award":["NRF-NRFI06-2020-0001"],"award-info":[{"award-number":["NRF-NRFI06-2020-0001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639217","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["An Empirical Study on Noisy Label Learning for Program Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0585-2136","authenticated-orcid":false,"given":"Wenhan","family":"Wang","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2263-7383","authenticated-orcid":false,"given":"Yanzhou","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3592-4153","authenticated-orcid":false,"given":"Anran","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8316-1894","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0044-466X","authenticated-orcid":false,"given":"Wei","family":"Ma","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.449"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Learning Representations.","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."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022873112823"},{"key":"e_1_3_2_1_6_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528446"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00022"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3171202"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3561168"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_2_1_13_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations.","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, LIU Shujie, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems 31","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606585"},{"key":"e_1_3_2_1_16_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196321.3196334"},{"key":"e_1_3_2_1_18_1","unstructured":"Xing Hu Ge Li Xin Xia David Lo Shuai Lu and Zhi Jin. 2018. Summarizing source code with transferred api knowledge. (2018)."},{"key":"e_1_3_2_1_19_1","volume-title":"On the impact of various types of noise on neural machine translation. arXiv preprint arXiv:1805.12282","author":"Khayrallah Huda","year":"2018","unstructured":"Huda Khayrallah and Philipp Koehn. 2018. On the impact of various types of noise on neural machine translation. arXiv preprint arXiv:1805.12282 (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International conference on machine learning. PMLR, 1885--1894."},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning","volume":"1","author":"Li Anran","year":"2023","unstructured":"Anran Li, Yue Cao, Jiabao Guo, Hongyi Peng, Qing Guo, and Han Yu. 2023. FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning. Proceedings of the ACM on Management of Data 1, 3 (2023), 1--24.","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488723"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3137321"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00039"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556941"},{"key":"e_1_3_2_1_26_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. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10139"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598037"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"e_1_3_2_1_32_1","first-page":"19920","article-title":"Estimating training data influence by tracing gradient descent","volume":"33","author":"Pruthi Garima","year":"2020","unstructured":"Garima Pruthi, Frederick Liu, Satyen Kale, and Mukund Sundararajan. 2020. Estimating training data influence by tracing gradient descent. Advances in Neural Information Processing Systems 33 (2020), 19920--19930.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Puri Ruchir","year":"2021","unstructured":"Ruchir Puri, David S Kung, Geert Janssen, Wei Zhang, Giacomo Domeniconi, Vladimir Zolotov, Julian Dolby, Jie Chen, Mihir Choudhury, Lindsey Decker, et al. 2021. CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549145"},{"key":"e_1_3_2_1_35_1","volume-title":"Meta-weight-net: Learning an explicit mapping for sample weighting. Advances in neural information processing systems 32","author":"Shu Jun","year":"2019","unstructured":"Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, and Deyu Meng. 2019. Meta-weight-net: Learning an explicit mapping for sample weighting. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"e_1_3_2_1_37_1","unstructured":"Weisong Sun Chunrong Fang Yudu You Yun Miao Yi Liu Yuekang Li Gelei Deng Shenghan Huang Yuchen Chen Quanjun Zhang et al. 2023. Automatic Code Summarization via ChatGPT: How Far Are We? arXiv preprint arXiv:2305.12865 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510160"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.521"},{"key":"e_1_3_2_1_40_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, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054857"},{"key":"e_1_3_2_1_42_1","volume-title":"International Conference on Learning Representations.","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00075"},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Machine Learning. PMLR, 7164--7173","author":"Yu Xingrui","year":"2019","unstructured":"Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor Tsang, and Masashi Sugiyama. 2019. How does disagreement help generalization against label corruption?. In International Conference on Machine Learning. PMLR, 7164--7173."},{"key":"e_1_3_2_1_45_1","volume-title":"Evaluating instruction-tuned large language models on code comprehension and generation. arXiv preprint arXiv:2308.01240","author":"Yuan Zhiqiang","year":"2023","unstructured":"Zhiqiang Yuan, Junwei Liu, Qiancheng Zi, Mingwei Liu, Xin Peng, and Yiling Lou. 2023. Evaluating instruction-tuned large language models on code comprehension and generation. arXiv preprint arXiv:2308.01240 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00086"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524610.3527905"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17319"},{"key":"e_1_3_2_1_49_1","volume-title":"Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks. Advances in neural information processing systems 32","author":"Zhou Yaqin","year":"2019","unstructured":"Yaqin Zhou, Shangqing Liu, Jingkai Siow, Xiaoning Du, and Yang Liu. 2019. Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_50_1","volume-title":"International Conference on Machine Learning. PMLR, 27412--27427","author":"Zhu Zhaowei","year":"2022","unstructured":"Zhaowei Zhu, Zihao Dong, and Yang Liu. 2022. Detecting corrupted labels without training a model to predict. In International Conference on Machine Learning. PMLR, 27412--27427."}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"],"location":"Lisbon Portugal","acronym":"ICSE '24"},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639217","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:13Z","timestamp":1750286953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":49,"alternative-id":["10.1145\/3597503.3639217","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639217","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}