{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T07:46:36Z","timestamp":1743925596762,"version":"3.37.3"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61836013"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Strategic Priority Research Program of CAS","award":["XDB31000000"]},{"name":"Chinese Academy of Sciences Network Security and Informatization Special Application Demonstration","award":["CAS-WX2021SF-0101-03"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Web"],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"\n Graph clustering has been a hot research topic and is widely used in many fields, such as community detection in social networks. Lots of works combining auto-encoder and graph neural networks have been applied to clustering tasks by utilizing node attributes and graph structure. These works usually assumed the inherent parameters (i.e., size and variance) of different clusters in the latent embedding space are homogeneous, and hence the assigned probability is monotonous over the Euclidean distance between node embeddings and centroids. Unfortunately, this assumption usually does not hold since the size and concentration of different clusters can be quite different, which limits the clustering accuracy. In addition, the node embeddings in deep graph clustering methods are usually L2 normalized so that it lies on the surface of a unit hyper-sphere. To solve this problem, we proposed\n \n D<\/jats:bold>\n <\/jats:underline>\n eep\n \n A<\/jats:bold>\n <\/jats:underline>\n daptive\n \n G<\/jats:bold>\n <\/jats:underline>\n raph\n \n C<\/jats:bold>\n <\/jats:underline>\n lustering via von Mises-Fisher distributions, namely DAGC. DAGC assumes the node embeddings\n \n H<\/jats:italic>\n <\/jats:bold>\n can be drawn from a von Mises-Fisher distribution and each cluster\n k<\/jats:italic>\n is associated with cluster inherent parameters\n \n \u03c1<\/jats:italic>\n <\/jats:bold>\n \n k<\/jats:italic>\n <\/jats:sub>\n which includes cluster center\n \u03bc<\/jats:bold>\n and cluster cohesion degree \u03ba. Then we adopt an EM-like approach (i.e., \ud835\udcab(\n \n H<\/jats:italic>\n <\/jats:bold>\n |\n \n \u03c1<\/jats:italic>\n <\/jats:bold>\n ) and \ud835\udcab(\n \n \u03c1<\/jats:italic>\n <\/jats:bold>\n |\n \n H<\/jats:italic>\n <\/jats:bold>\n ), respectively) to learn the embedding and cluster inherent parameters alternately. Specifically, with the node embeddings, we proposed to update the cluster centers in an attraction-repulsion manner to make the cluster centers more separable. And given the cluster inherent parameters, a likelihood-based loss is proposed to make node embeddings more concentrated around cluster centers. Thus, DAGC can simultaneously improve the intra-cluster compactness and inter-cluster heterogeneity. Finally, extensive experiments conducted on four benchmark datasets have demonstrated that the proposed DAGC consistently outperforms the state-of-the-art methods, especially on imbalanced datasets.\n <\/jats:p>","DOI":"10.1145\/3580521","type":"journal-article","created":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T12:10:07Z","timestamp":1675167007000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep Adaptive Graph Clustering via von Mises-Fisher Distributions"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1075-0684","authenticated-orcid":false,"given":"Pengfei","family":"Wang","sequence":"first","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3354-0973","authenticated-orcid":false,"given":"Daqing","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University; DAMO Academy, Alibaba Group, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0213-9957","authenticated-orcid":false,"given":"Chong","family":"Chen","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6053-5977","authenticated-orcid":false,"given":"Kunpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Portland State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-8024","authenticated-orcid":false,"given":"Yanjie","family":"Fu","sequence":"additional","affiliation":[{"name":"University of Central Florida, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5735-2910","authenticated-orcid":false,"given":"Jianqiang","family":"Huang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2144-1131","authenticated-orcid":false,"given":"Yuanchun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3728-6837","authenticated-orcid":false,"given":"Jianfeng","family":"Zhan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8232-5049","authenticated-orcid":false,"given":"Xiansheng","family":"Hua","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}]}],"member":"320","published-online":{"date-parts":[[2024,1,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2016.2601022"},{"key":"e_1_3_2_3_2","first-page":"1961","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Altschuler Jason","year":"2017","unstructured":"Jason Altschuler, Jonathan Niles-Weed, and Philippe Rigollet. 2017. Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS). 1961\u20131971."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088718"},{"key":"e_1_3_2_5_2","article-title":"Graph convolution for semi-supervised classification: Improved linear separability and out-of-distribution generalization","author":"Baranwal Aseem","year":"2021","unstructured":"Aseem Baranwal, Kimon Fountoulakis, and Aukosh Jagannath. 2021. Graph convolution for semi-supervised classification: Improved linear separability and out-of-distribution generalization. arXiv preprint arXiv:2102.06966 (2021).","journal-title":"arXiv preprint arXiv:2102.06966"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380214"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403140"},{"key":"e_1_3_2_10_2","article-title":"Semantic instance segmentation with a discriminative loss function","author":"Brabandere Bert De","year":"2017","unstructured":"Bert De Brabandere, Davy Neven, and Luc Van Gool. 2017. Semantic instance segmentation with a discriminative loss function. arXiv preprint arXiv:1708.02551 (2017).","journal-title":"arXiv preprint arXiv:1708.02551"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/599609.599630"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2430659"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/467"},{"key":"e_1_3_2_14_2","first-page":"154","volume-title":"International Conference on Machine Learning","author":"Gopal Siddharth","year":"2014","unstructured":"Siddharth Gopal and Yiming Yang. 2014. Von Mises-Fisher clustering models. In International Conference on Machine Learning. PMLR, 154\u2013162."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/243"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00849"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16951"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018667"},{"key":"e_1_3_2_22_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"e_1_3_2_23_2","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf Thomas N.","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).","journal-title":"arXiv preprint arXiv:1609.02907"},{"key":"e_1_3_2_24_2","article-title":"Variational graph auto-encoders","author":"Kipf Thomas N.","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. ArXiv abs\/1611.07308 (2016).","journal-title":"ArXiv abs\/1611.07308"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.139"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132919"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00909"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330868"},{"key":"e_1_3_2_29_2","unstructured":"L. Lov\u00e1sz and M. D. Plummer. 1986. Matching Theory . (1986)."},{"key":"e_1_3_2_30_2","article-title":"Graph entropy guided node embedding dimension selection for graph neural networks","author":"Luo Gongxu","year":"2021","unstructured":"Gongxu Luo, Jianxin Li, Jianlin Su, Hao Peng, Carl Yang, Lichao Sun, Philip S. Yu, and Lifang He. 2021. Graph entropy guided node embedding dimension selection for graph neural networks. arXiv preprint arXiv:2105.03178 (2021).","journal-title":"arXiv preprint arXiv:2105.03178"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.07.029"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.3390\/make1030055"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104772"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932096"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490181"},{"key":"e_1_3_2_36_2","article-title":"Reinforced, incremental and cross-lingual event detection from social messages","author":"Peng Hao","year":"2022","unstructured":"Hao Peng, Ruitong Zhang, Shaoning Li, Yuwei Cao, Shirui Pan, and Philip Yu. 2022. Reinforced, incremental and cross-lingual event detection from social messages. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_37_2","article-title":"Attention-driven graph clustering network","author":"Peng Zhihao","year":"2021","unstructured":"Zhihao Peng, Hui Liu, Yuheng Jia, and Junhui Hou. 2021. Attention-driven graph clustering network. arXiv preprint arXiv:2108.05499 (2021).","journal-title":"arXiv preprint arXiv:2108.05499"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005458"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Z. Qiao P. Wang Y. Fu Y. Du and Y. Zhou. 2020. Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning.","DOI":"10.1109\/ICDM50108.2020.00052"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00067"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2007.05.001"},{"key":"e_1_3_2_42_2","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur Oleksandr","year":"2018","unstructured":"Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2018. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018).","journal-title":"arXiv preprint arXiv:1811.05868"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.2307\/2314570"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-16142-2_14"},{"key":"e_1_3_2_45_2","first-page":"1","article-title":"Network embedding for community detection in attributed networks","volume":"14","author":"Sun Heli","year":"2020","unstructured":"Heli Sun, Fang He, Jianbin Huang, Yizhou Sun, Yang Li, Chenyu Wang, Liang He, Zhongbin Sun, and Xiaolin Jia. 2020. Network embedding for community detection in attributed networks. ACM Transactions on Knowledge Discovery from Data 14 (2020), 1\u201325.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8916"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17198"},{"key":"e_1_3_2_48_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/509"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.082"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098067"},{"key":"e_1_3_2_52_2","article-title":"You are how you drive: Peer and temporal-aware representation learning for driving behavior analysis","author":"Wang P.","year":"2018","unstructured":"P. Wang, Y. Fu, J. Zhang, P. Wang, Y. Zheng, and C. C. Aggarwal. 2018. You are how you drive: Peer and temporal-aware representation learning for driving behavior analysis. ACM (2018).","journal-title":"ACM"},{"issue":"3","key":"e_1_3_2_53_2","article-title":"Spotting trip purposes from taxi trajectories: A general probabilistic model","volume":"9","author":"Wang P.","year":"2018","unstructured":"P. Wang, G. Liu, Y. Fu, Y. Zhou, and J. Li. 2018. Spotting trip purposes from taxi trajectories: A general probabilistic model. ACM Transactions on Intelligent Systems 9, 3 (2018), 29.1\u201329.26.","journal-title":"ACM Transactions on Intelligent Systems"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8950"},{"key":"e_1_3_2_56_2","first-page":"478","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Xie Junyuan","year":"2016","unstructured":"Junyuan Xie, Ross Girshick, and Ali Farhadi. 2016. Unsupervised deep embedding for clustering analysis. In Proceedings of the International Conference on Machine Learning (ICML). 478\u2013487."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/2540128.2540388"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1137\/20M1386062"},{"key":"e_1_3_2_59_2","first-page":"2111","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","author":"Yang Cheng","year":"2015","unstructured":"Cheng Yang, Zhiyuan Liu, Deli Zhao, Maosong Sun, and Edward Chang. 2015. Network representation learning with rich text information. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). 2111\u20132117."},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00654"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623715"},{"key":"e_1_3_2_62_2","article-title":"Unsupervised deep manifold attributed graph embedding","author":"Zang Zelin","year":"2021","unstructured":"Zelin Zang, Siyuan Li, Di Wu, Jianzhu Guo, Yongjie Xu, and Stan Z. Li. 2021. Unsupervised deep manifold attributed graph embedding. arXiv preprint arXiv:2104.13048 (2021).","journal-title":"arXiv preprint arXiv:2104.13048"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2850013"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/601"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.05.026"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380076"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687709"}],"container-title":["ACM Transactions on the Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T09:53:25Z","timestamp":1704707605000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580521"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,8]]},"references-count":66,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3580521"],"URL":"https:\/\/doi.org\/10.1145\/3580521","relation":{},"ISSN":["1559-1131","1559-114X"],"issn-type":[{"type":"print","value":"1559-1131"},{"type":"electronic","value":"1559-114X"}],"subject":[],"published":{"date-parts":[[2024,1,8]]},"assertion":[{"value":"2022-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}