{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:32:07Z","timestamp":1772119927142,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2209814,IIS-2203262,IIS-2214376,CNS-2203261,CNS-1814825,IIS-2217239,IIS-2027127,OAC-2218762"],"award-info":[{"award-number":["IIS-2209814,IIS-2203262,IIS-2214376,CNS-2203261,CNS-1814825,IIS-2217239,IIS-2027127,OAC-2218762"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005289","name":"National Institute of Justice","doi-asserted-by":"publisher","award":["2018-75-CX-0032"],"award-info":[{"award-number":["2018-75-CX-0032"]}],"id":[{"id":"10.13039\/100005289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539324","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"1390-1400","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Rep2Vec: Repository Embedding via Heterogeneous Graph Adversarial Contrastive Learning"],"prefix":"10.1145","author":[{"given":"Yiyue","family":"Qian","sequence":"first","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}]},{"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, OH, USA"}]},{"given":"Qianlong","family":"Wen","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}]},{"given":"Yanfang","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}]},{"given":"Chuxu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Brandeis University, Waltham, MA, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2017. virustotal: R Client for the VirusTotal API. https:\/\/cran.r-project.org\/web\/ packages\/virustotal\/index.html."},{"key":"e_1_3_2_2_2_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML."},{"key":"e_1_3_2_2_3_1","volume-title":"Bert: Pre-training 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. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Yuxiao Dong Nitesh V Chawla and Ananthram Swami. 2017. metapath2vec: Scalable representation learning for heterogeneous networks. In KDD.","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In KDD.","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_2_2_6_1","unstructured":"Kathy J Horadam. 2012. Hadamard matrices and their applications. Princeton university press."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Shifu Hou Yujie Fan Yiming Zhang Yanfang Ye Jingwei Lei Wenqiang Wan JiabinWang Qi Xiong and Fudong Shao. 2019. \"cyber: Enhancing robustness of android malware detection system against adversarial attacks on heterogeneous graph based model. In CIKM.","DOI":"10.1145\/3357384.3357875"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098026"},{"key":"e_1_3_2_2_9_1","volume-title":"Towards robust graph contrastive learning. arXiv preprint arXiv:2102.13085","author":"Nikola","year":"2021","unstructured":"Nikola Jovanovi?, Zhao Meng, Lukas Faber, and Roger Wattenhofer. 2021. Towards robust graph contrastive learning. arXiv preprint arXiv:2102.13085 (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"Adam: A method for stochastic optimization. In ICLR.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR."},{"key":"e_1_3_2_2_11_1","volume-title":"Variational graph auto-encoders. arXiv preprint arXiv:1611.07308","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)."},{"key":"e_1_3_2_2_12_1","unstructured":"Thomas N Kipf and MaxWelling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Miika Koskela Inka Simola and Kostas Stefanidis. 2018. Open source software recommendations using github. In TPDL.","DOI":"10.1007\/978-3-030-00066-0_24"},{"key":"e_1_3_2_2_14_1","unstructured":"Anders Krogh and John Hertz. 1991. A simple weight decay can improve generalization. In NeurIPS."},{"key":"e_1_3_2_2_15_1","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In ICLR."},{"key":"e_1_3_2_2_16_1","volume-title":"Applied logistic regression analysis","author":"Menard Scott","unstructured":"Scott Menard. 2002. Applied logistic regression analysis. Sage."},{"key":"e_1_3_2_2_17_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Yiyue Qian Yiming Zhang Yanfang Ye and Chuxu Zhang. 2021. Adapting Meta Knowledge with Heterogeneous Information Network for COVID-19 Themed Malicious Repository Detection. In IJCAI.","DOI":"10.24963\/ijcai.2021\/507"},{"key":"e_1_3_2_2_20_1","unstructured":"Yiyue Qian Yiming Zhang Yanfang Ye and Chuxu Zhang. 2021. Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media. In NeurIPS."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"e_1_3_2_2_22_1","unstructured":"Md Omar Faruk Rokon Risul Islam Ahmad Darki Evangelos E Papalexakis and Michalis Faloutsos. 2020. Sourcefinder Finding malware source-code from publicly available repositories in github. In RAID."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Md Omar Faruk Rokon Pei Yan Risul Islam and Michalis Faloutsos. 2021. Repo2vec: A comprehensive embedding approach for determining repository similarity. In ICSME.","DOI":"10.26226\/morressier.613b5418842293c031b5b614"},{"key":"e_1_3_2_2_24_1","volume-title":"Ivan Titov, and MaxWelling.","author":"Schlichtkrull Michael","year":"2018","unstructured":"Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and MaxWelling. 2018. Modeling relational data with graph convolutional networks. In ESWC."},{"key":"e_1_3_2_2_25_1","volume-title":"Deep learning in neural networks: An overview. Neural networks","author":"Schmidhuber J\u00fcrgen","year":"2015","unstructured":"J\u00fcrgen Schmidhuber. 2015. Deep learning in neural networks: An overview. Neural networks (2015)."},{"key":"e_1_3_2_2_26_1","unstructured":"Semmle. 2019. CodeQL for research. https:\/\/securitylab.github.com\/tools\/codeql."},{"key":"e_1_3_2_2_27_1","unstructured":"Semmle. 2019. LGTM. https:\/\/github.com\/marketplace\/lgtm."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Huajie Shao Dachun Sun Jiahao Wu Zecheng Zhang Aston Zhang Shuochao Yao Shengzhong Liu Tianshi Wang Chao Zhang and Tarek Abdelzaher. 2020. paper2repo: GitHub repository recommendation for academic papers. In WWW.","DOI":"10.1145\/3366423.3380145"},{"key":"e_1_3_2_2_29_1","volume-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In ICLR.","author":"Sun Fan-Yun","year":"2020","unstructured":"Fan-Yun Sun, Jordan Hoffmann, Vikas Verma, and Jian Tang. 2020. Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In ICLR."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402736"},{"key":"e_1_3_2_2_31_1","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR."},{"key":"e_1_3_2_2_32_1","unstructured":"Petar Velickovic William Fedus William L Hamilton Pietro Li\u00f2 Yoshua Bengio and R Devon Hjelm. 2019. Deep Graph Infomax. In ICLR."},{"key":"e_1_3_2_2_33_1","volume-title":"Graphgan: Graph representation learning with generative adversarial nets. In AAAI.","author":"Wang Hongwei","year":"2018","unstructured":"Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018. Graphgan: Graph representation learning with generative adversarial nets. In AAAI."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Xiao Wang Houye Ji Chuan Shi Bai Wang Yanfang Ye Peng Cui and Philip S Yu. 2019. Heterogeneous graph attention network. In WWW.","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Xiao Wang Nian Liu Hui Han and Chuan Shi. 2021. Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning. In KDD.","DOI":"10.1145\/3447548.3467415"},{"key":"e_1_3_2_2_36_1","volume-title":"Contrastive learning with stronger augmentations. arXiv preprint arXiv:2104.07713","author":"Wang Xiao","year":"2021","unstructured":"Xiao Wang and Guo-Jun Qi. 2021. Contrastive learning with stronger augmentations. arXiv preprint arXiv:2104.07713 (2021)."},{"key":"e_1_3_2_2_37_1","unstructured":"Wikipedia. 2022. GitHub Introduction. https:\/\/en.wikipedia.org\/wiki\/GitHub."},{"key":"e_1_3_2_2_38_1","volume-title":"A survey on malware detection using data mining techniques. ACM Computing Surveys (CSUR)","author":"Ye Yanfang","year":"2017","unstructured":"Yanfang Ye, Tao Li, Donald Adjeroh, and S Sitharama Iyengar. 2017. A survey on malware detection using data mining techniques. ACM Computing Surveys (CSUR) (2017)."},{"key":"e_1_3_2_2_39_1","unstructured":"Yuning You Tianlong Chen Yongduo Sui Ting Chen Zhangyang Wang and Yang Shen. 2020. Graph contrastive learning with augmentations. In NeurIPS."},{"key":"e_1_3_2_2_40_1","volume-title":"SAIL: Self-Augmented Graph Contrastive Learning. In AAAI.","author":"Yu Lu","year":"2022","unstructured":"Lu Yu, Shichao Pei, Lizhong Ding, Jun Zhou, Longfei Li, Chuxu Zhang, and Xiangliang Zhang. 2022. SAIL: Self-Augmented Graph Contrastive Learning. In AAAI."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Chuxu Zhang Dongjin Song Chao Huang Ananthram Swami and Nitesh V Chawla. 2019. Heterogeneous graph neural network. In KDD.","DOI":"10.1145\/3292500.3330961"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291001"},{"key":"e_1_3_2_2_43_1","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link Prediction Based on Graph Neural Networks. In NeurIPS."},{"key":"e_1_3_2_2_44_1","volume-title":"Gnnguard: Defending graph neural networks against adversarial attacks. In NeurIPS.","author":"Zhang Xiang","year":"2020","unstructured":"Xiang Zhang and Marinka Zitnik. 2020. Gnnguard: Defending graph neural networks against adversarial attacks. In NeurIPS."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Yiming Zhang Yujie Fan Shifu Hou Yanfang Ye Xusheng Xiao Pan Li Chuan Shi Liang Zhao and Shouhuai Xu. 2020. Cyber-guided Deep Neural Network for Malicious Repository Detection in GitHub. In ICKG.","DOI":"10.1109\/ICBK50248.2020.00071"},{"key":"e_1_3_2_2_46_1","volume-title":"Xin Xia, Quanlai Li, and Jianling Sun.","author":"Zhang Yun","year":"2017","unstructured":"Yun Zhang, David Lo, Pavneet Singh Kochhar, Xin Xia, Quanlai Li, and Jianling Sun. 2017. Detecting similar repositories on GitHub. In SANER."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Yiming Zhang Yiyue Qian Yujie Fan Yanfang Ye Xin Li Qi Xiong and Fudong Shao. 2020. dstyle-gan: Generative adversarial network based on writing and photography styles for drug identification in darknet markets. In ACSAC.","DOI":"10.1145\/3427228.3427603"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Yiming Zhang Yiyue Qian Yanfang Ye and Chuxu Zhang. 2022. Adapting Distilled Knowledge for Few-shot Relation Reasoning over Knowledge Graphs. In SDM.","DOI":"10.1137\/1.9781611977172.75"},{"key":"e_1_3_2_2_49_1","volume-title":"Higitclass: Keyword-driven hierarchical classification of github repositories. In ICDM.","author":"Zhang Yu","year":"2019","unstructured":"Yu Zhang, Frank F Xu, Sha Li, Yu Meng, Xuan Wang, Qi Li, and Jiawei Han. 2019. Higitclass: Keyword-driven hierarchical classification of github repositories. In ICDM."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"Jianan Zhao Qianlong Wen Shiyu Sun Yanfang Ye and Chuxu Zhang. 2021. Multi-view Self-supervised Heterogeneous Graph Embedding. In ECML\/PKDD.","DOI":"10.1007\/978-3-030-86520-7_20"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Daniel Z\u00fcgner Amir Akbarnejad and Stephan G\u00fcnnemann. 2018. Adversarial attacks on neural networks for graph data. In KDD.","DOI":"10.1145\/3219819.3220078"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539324","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539324","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:47Z","timestamp":1750186967000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":51,"alternative-id":["10.1145\/3534678.3539324","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539324","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}