{"id":108,"date":"2021-09-18T05:03:08","date_gmt":"2021-09-18T09:03:08","guid":{"rendered":"https:\/\/sites.nd.edu\/xiangliang-zhang\/?page_id=108"},"modified":"2026-01-29T20:50:01","modified_gmt":"2026-01-30T01:50:01","slug":"learning-for-graphs-networks","status":"publish","type":"page","link":"https:\/\/sites.nd.edu\/xiangliang-zhang\/learning-for-graphs-networks\/","title":{"rendered":"Learning with Graphs\/Networks"},"content":{"rendered":"\n<p class=\"has-medium-font-size wp-block-paragraph\">We design machine learning models for solving diverse graph\/network problems, such as  <strong>attributed network embedding<\/strong>, <strong>knowledge graph alignment<\/strong>, <strong>knowledge graph completion<\/strong>, <strong>dynamic graph modeling<\/strong>, <strong>spatial-temporal network embedding<\/strong> and <strong>influential nodes tracking in dynamic networks<\/strong>.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Yijun Tian, Chuxu Zhang, Ziyi Kou, Zheyuan Liu, Xiangliang Zhang, Nitesh V Chawla. Adaptive and Context-rich Generative Self-supervised Learning on Graphs. Accepted by <strong>AAAI 2026<\/strong>. (4,167 out of 23,680 submissions, acceptance rate 17.6%)<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Zichong Wang, Nhat Hoang, Xingyu Zhang, Kevin Bello, Xiangliang Zhang, Sundararaja Sitharama Iyengar, Wenbin Zhang. Towards Fair Graph Learning without Demographic Information. Accepted by <strong>AISTATS 2025<\/strong>.<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Qiannan Zhang, Shichao Pei, Yuan Fang, Xiangliang Zhang. Unlocking the Potential of Black-box Pre-trained GNNs for Graph Few-shot Learning. <strong>AAAI<\/strong> 2025.<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Yijun Tian, Shichao Pei, Xiangliang Zhang, Chuxu Zhang, Nitesh V. Chawla. <a href=\"https:\/\/arxiv.org\/abs\/2302.00219\" data-type=\"link\" data-id=\"https:\/\/arxiv.org\/abs\/2302.00219\">Knowledge Distillation on Graphs: A Survey<\/a>. To appear in <strong>ACM Computing Surveys.<\/strong><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Rui Cai, Shichao Pei, Xiangliang Zhang. <a href=\"https:\/\/www.computer.org\/csdl\/proceedings-article\/bigdata\/2024\/10825189\/23ykGHbrvHy\">Zero-Shot Relational Learning for Multimodal Knowledge Graphs<\/a>. The 2024 IEEE International Conference on <strong>Big Data<\/strong> (Regular paper, acceptance rate: 18.8% 124 out of 660 submissions)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Xiaoting Lyu, Yufei Han, Wei Wang, Hangwei Qian, Ivor Tsang, Xiangliang Zhang. <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671956\">Cross-Context Backdoor Attacks against Graph Prompt Learning.<\/a> Accepted by the 30th SIGKDD Conference on Knowledge Discovery and Data Mining (<strong>KDD 2024<\/strong>). Barcelona, Spain, Sunday 25 August 2024 \u2013 Thursday 29 August 2024.<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Changsheng Ma, Taicheng Guo, Qiang Yang, Xiuying Chen, Xin Gao, Shangsong Liang, Nitesh Chawla, Xiangliang Zhang. <a href=\"https:\/\/ieeexplore.ieee.org\/document\/10447350\">A Property-Guided Diffusion Model for Generating Molecular Graphs<\/a>. <strong>IEEE ICASSP 2024<\/strong>.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Zhenwei Tang, Shichao Pei, Xi Peng, Fuzhen Zhuang, Xiangliang Zhang and Robert Hoehndorf. Neural Multi-hop Logical Query Answering with Concept-level Answers. The 22nd International Semantic Web Conference (<strong><a href=\"https:\/\/iswc2023.semanticweb.org\/\">ISWC 2023<\/a><\/strong>).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shichao Pei, Ziyi Kou, Qiannan Zhang, Xiangliang Zhang. Few-shot Low-resource Knowledge Graph Completion with Multi-view Task Representation Generation. Accepted by <strong><a href=\"https:\/\/kdd.org\/kdd2023\/\">KDD 2023<\/a><\/strong>. Long Beach, CA. Aug 6-13, 2023. (acceptance rate = 313\/1416 = 22%)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Qiang Yang, Changsheng Ma, Qiannan Zhang, Xin Gao, Chuxu Zhang, Xiangliang Zhang. Counterfactual Learning on Heterogeneous Graphs with Greedy Perturbation. Accepted by <strong><a href=\"https:\/\/kdd.org\/kdd2023\/\">KDD 2023<\/a><\/strong>. Long Beach, CA. Aug 6-13, 2023. (acceptance rate = 313\/1416 = 22%)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shichao Pei, Qiannan Zhang, Xiangliang Zhang. Few-shot Low-resource Knowledge Graph Completion with Reinforced Task Generation. <a href=\"https:\/\/aclanthology.org\/2023.findings-acl.455\/\" data-type=\"URL\" data-id=\"https:\/\/aclanthology.org\/2023.findings-acl.455\/\"><strong>Findings of ACL 2023<\/strong><\/a><strong>.<\/strong> <\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Zhichun Guo,&nbsp; Kehan Guo, Bozhao Nan, Yijun Tian, Roshni Iyer, Yihong Ma, Olaf Wiest, Xiangliang Zhang,&nbsp;Wei Wang, Chuxu Zhang, Nitesh Chawla. Graph-based Molecular Representation Learning. Accepted by The 32nd International Joint Conference on Artificial Intelligence (<strong><a href=\"https:\/\/ijcai-23.org\/\" data-type=\"URL\" data-id=\"https:\/\/ijcai-23.org\/\">IJCAI-23<\/a><\/strong>). 19th-25th August 2023. Macao, S.A.R. (Survey)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Zhenwei Tang, Griffin Floto, Armin Toroghi, Shichao Pei, Xiangliang Zhang and Scott Sanner LogicRec: Recommendation with Users&#8217; Logical Requirements. Accepted by <strong><a href=\"https:\/\/sigir.org\/sigir2023\/\" data-type=\"URL\" data-id=\"https:\/\/sigir.org\/sigir2023\/\">SIGIR 2023<\/a><\/strong> (Short paper, Acceptance rate = 154\/613 = 25.12%)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Yijun Tian, Chuxu Zhang, Zhichun Guo, Xiangliang Zhang, Nitesh Chawla. Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency. Accepted (<strong>notable-top-25%<\/strong>) by the  11th International Conference on Learning Representations (<strong><a href=\"https:\/\/iclr.cc\/\" data-type=\"URL\" data-id=\"https:\/\/iclr.cc\/\">ICLR 2023<\/a><\/strong>). Kigali, Rwanda, May 1-5, 2023.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Qiannan Zhang, Shichao Pei, Qiang Yang, Chuxu Zhang, Nitesh Chawla, Xiangliang Zhang. Cross-domain Few-shot Graph Classification with a Reinforced Task Coordinator. Accepted by the Thirty-Seventh AAAI Conference on Artificial Intelligence (<a href=\"https:\/\/aaai.org\/Conferences\/AAAI-23\/\" data-type=\"URL\" data-id=\"https:\/\/aaai.org\/Conferences\/AAAI-23\/\"><strong>AAAI 2023<\/strong><\/a>). Feb 7-14, 2023 Washington DC. (Acceptance rate = 19.6% \uff081,721 of 8,777 submissions))<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Qiang Yang, Changsheng Ma, Qiannan Zhang, Xin Gao, Chuxu Zhang, Xiangliang Zhang. Interpretable Research Interest Shift Detection with Temporal Heterogeneous Graphs. ACM International Conference on Web Search and Data Mining (<a href=\"https:\/\/www.wsdm-conference.org\/2023\/\" data-type=\"URL\" data-id=\"https:\/\/www.wsdm-conference.org\/2023\/\"><strong>WSDM 2023<\/strong><\/a>). Singapore February 27 to March 3, 2023.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Qiannan Zhang, Xiaodong Wu,&nbsp;Qiang Yang,&nbsp;Chuxu Zhang,&nbsp;Xiangliang Zhang. Few-shot Heterogeneous Graph Learning via Cross-domain Knowledge Transfer. Accepted at <strong><a rel=\"noreferrer noopener\" href=\"https:\/\/kdd.org\/kdd2022\/\" data-type=\"URL\" data-id=\"https:\/\/kdd.org\/kdd2022\/\" target=\"_blank\">KDD 2022 Research Track<\/a><\/strong>. August 14-18, 2022, in Washington, DC (Acceptance Rate:&nbsp; 254\/1695&nbsp; = 15%)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Zhenwei Tang, Shichao Pei, Zhao Zhang, Yongchun Zhu, Fuzhen Zhuang, Robert Hoehndorf, Xiangliang Zhang. Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion. Accepted by the 31st International Joint Conference on Artificial Intelligence (<strong><a href=\"https:\/\/ijcai-22.org\/\" data-type=\"URL\" data-id=\"https:\/\/ijcai-22.org\/\">IJCAI 2022<\/a><\/strong>). (acceptance rate =15%, 681 out of 4535 submissions).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Chuxu Zhang, Kaize Ding, Jundong Li, Xiangliang Zhang, Yanfang Ye, Nitesh Chawla, Huan Liu. Few-Shot Learning on Graphs: A Survey.  The 31st International Joint Conference on Artificial Intelligence &#8211; Survey Track. (<strong><a href=\"https:\/\/ijcai-22.org\/\" data-type=\"URL\" data-id=\"https:\/\/ijcai-22.org\/\">IJCAI 2022<\/a><\/strong>).  Early Access <a href=\"https:\/\/arxiv.org\/abs\/2203.09308\" data-type=\"URL\" data-id=\"https:\/\/arxiv.org\/abs\/2203.09308\">on arXiv<\/a><\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shichao Pei, Lu Yu, Guoxian Yu and Xiangliang Zhang. Graph Alignment with Noisy Supervision. Accepted by <a rel=\"noreferrer noopener\" href=\"https:\/\/www2022.thewebconf.org\/\" target=\"_blank\">TheWebConf 2022<\/a>. (Acceptance rate: 323\/1822 =17.7%)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Qiannan Zhang, Xiaodong Wu, Qiang Yang, Chuxu Zhang, Xiangliang Zhang. HG-Meta: Graph Meta-learning over Heterogeneous Graphs. Accepted by SIAM International Conference on Data Mining (<strong><a href=\"https:\/\/www.siam.org\/conferences\/cm\/conference\/sdm22\">SDM 2022<\/a><\/strong>) acceptance rate: 83\/298 = 27.8%).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Wei Wang, Xiangyu Wei, Xiaoyang Suo, Bin Wang, Hao Wang, Hong-Ning Dai, Xiangliang Zhang. &#8220;HGATE: Heterogeneous Graph Attention Auto-Encoders&#8221;. To appear in &nbsp;IEEE Transactions on Knowledge and Data Engineering (<a href=\"https:\/\/ieeexplore.ieee.org\/document\/9448379\"><strong>TKDE<\/strong><\/a>).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Lu Yu, Shichao Pei, Lizhong Ding, Jun Zhou, Longfei Li, Chuxu Zhang, Xiangliang Zhang. SAIL: Self-Augmented Graph Contrastive Learning. <span style=\"color: initial;, sans-serif\">Accepted by the <a rel=\"noreferrer noopener\" href=\"https:\/\/aaai.org\/Conferences\/AAAI-22\/\" target=\"_blank\">Thirty-Sixth AAAI Conference on Artificial Intelligence (<strong>AAAI 2022<\/strong>)<\/a> (acceptance rate = 1349\/9020 = 15%)<\/span><\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li><span style=\"color: initial;, sans-serif\">Peng Han, Peilin Zhao, Chan Lu, Junzhou Huang, Jiaxiang Wu, Shuo Shang, Bin Yao, Xiangliang Zhang. GNN-Retro: Retrosynthetic planning with Graph Neural Networks. Accepted by the <a rel=\"noreferrer noopener\" href=\"https:\/\/aaai.org\/Conferences\/AAAI-22\/\" target=\"_blank\">Thirty-Sixth AAAI Conference on Artificial Intelligence (<strong>AAAI 2022<\/strong>)<\/a> (acceptance rate = 1349\/9020 = 15%)<\/span><\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li><span style=\"color: initial;, sans-serif\">Qiang Yang, Qiannan Zhang, Chuxu Zhang, Xiangliang Zhang. Interpretable Relation Learning on Heterogeneous Graphs. Accepted by The <a rel=\"noreferrer noopener\" href=\"https:\/\/www.wsdm-conference.org\/2022\/\" data-type=\"URL\" data-id=\"https:\/\/www.wsdm-conference.org\/2022\/\" target=\"_blank\">Fifteenth International Conference on Web Search and Data Mining (<strong>WSDM 2022<\/strong>)<\/a>. (acceptance rate = 159\/786 = 20.23%)<\/span><\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Tong Chen; Hongzhi Yin; Jie Ren; Zi Huang; Xiangliang Zhang; Hao Wang. Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning. To appear in<a href=\"https:\/\/ieeexplore.ieee.org\/xpl\/RecentIssue.jsp?punumber=69\">&nbsp;IEEE Transactions on Knowledge and Data Engineering (<strong>TKDE<\/strong><\/a>),&nbsp;2021.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Peng Han, Jin Wang, Di Yao, Shuo Shang, and Xiangliang Zhang. A Graph-based Approach for Trajectory Similarity Computation in Spatial Networks. &nbsp;<a href=\"https:\/\/www.kdd.org\/kdd2021\/\">ACM SIGKDD Conference on Knowledge Discovery and Data Mining (<strong>KDD<\/strong> 2021)<\/a>. Virtual Conference. Aug 14-18, 2021. (Acceptance Rate = 238\/1541 = 15.4%)<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Muhammad Imran, Hongzhi Yin, Tong Chen, Zi Huang, Xiangliang Zhang, Kai Zheng. DDHH: A Decentralized Deep Learning Framework for Large-scale Heterogeneous Networks. IEEE 37th&nbsp;<a href=\"https:\/\/icde2021.gr\/\">International Conference on Data Engineering (<strong>ICDE<\/strong> 2021)<\/a>, Greece, April, 2021. (6-Page Short Paper)<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Xin Xia, Hongzhi Yin, Junliang Yu, Qinyong Wang, Lizhen Cui, and Xiangliang Zhang. Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation. T<a href=\"https:\/\/aaai.org\/Conferences\/AAAI-21\/\">he Thirty-Fifth AAAI Conference on Artificial Intelligence (<strong>AAAI 2021<\/strong>)\u200b<\/a>&nbsp;\u200b (acceptance rate of 21%, 1692\/7911).<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Shupeng Gui,&nbsp;Xiangliang Zhang, Pan Zhong, Shuang Qiu, Mingrui Wu, Jieping Ye, Zhengdao Wang, Ji Liu, Pine: Universal deep embedding for graph nodes via partial permutation invariant set functions. To appear in &nbsp;<a href=\"https:\/\/ieeexplore.ieee.org\/xpl\/RecentIssue.jsp?punumber=34\">IEEE Transactions on Pattern Analysis and Machine Intelligence (<strong>T-PAMI<\/strong>)<\/a>, 2021.&nbsp;<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Shichao Pei, Lu Yu, Xiangliang Zhang. Set-aware Entity Synonym Discovery with Flexible Receptive Fields. &nbsp;IEEE Transactions on Knowledge and Data Engineering (<a href=\"https:\/\/ieeexplore.ieee.org\/document\/9448379\"><strong>TKDE<\/strong><\/a>). 2021. Early Access. <a rel=\"noreferrer noopener\" target=\"_blank\" href=\"https:\/\/doi.org\/10.1109\/TKDE.2021.3087532\">10.1109\/TKDE.2021.3087532<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Peng Han, Shuo Shang, Aixin Sun, Peilin Zhao, Kai Zheng, Xiangliang Zhang,&nbsp;\u201cPoint-of-Interest Recommendation with Global and Local Context\u201d. &nbsp;<a href=\"https:\/\/ieeexplore.ieee.org\/xpl\/RecentIssue.jsp?punumber=69\">IEEE Transactions on Knowledge and Data Engineering (<strong>TKDE<\/strong>)\u200b,<\/a>&nbsp;2021. Early Access: <a rel=\"noreferrer noopener\" target=\"_blank\" href=\"https:\/\/doi.org\/10.1109\/TKDE.2021.3059744\">10.1109\/TKDE.2021.3059744<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Uchenna Akujuobi, Jun Chen, Mohamed Elhoseiny, Michael Spranger, and Xiangliang Zhang. Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation. Accepted by&nbsp;<a href=\"https:\/\/nips.cc\/Conferences\/2020\">Neural Information Processing Systems (<strong>NeurIPS<\/strong> 2020)<\/a>. Virtual-only Conference. (Acceptance rate = 1900 \/9454 = 20%).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shichao Pei, Lu Yu, Guoxian Yu and Xiangliang Zhang. REA: Robust Cross-lingual Entity Alignment Between Knowledge Graphs. The<a href=\"https:\/\/www.kdd.org\/kdd2020\/\"> 26th SIGKDD Conference on Knowledge Discovery and Data Mining (<strong>KDD 2020<\/strong>)<\/a>, August 22 &#8211; 27, 2020, San Diego, CA, USA. &nbsp;(Acceptance rate 216\/1279=16.9%).\u200b<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Chuxu Zhang, Meng Jiang, Xiangliang Zhang, Yanfang Ye, Nitesh V. Chawla: Multi-modal Network Representation Learning. KDD 2020: 3557-3558. &nbsp;<a href=\"https:\/\/www.kdd.org\/kdd2020\/\">26th SIGKDD Conference on Knowledge Discovery and Data Mining <strong>(KDD<\/strong> 2020)<\/a>, pp. 3557-3558\u200b\u200b, August 22 \u2013 27, 2020, San Diego, CA, USA. [<a href=\"https:\/\/chuxuzhang.github.io\/KDD20_Tutorial.html\">Lecture-Style Tutorials<\/a>]<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Zaiqiao Meng, Shangsong Liang, Xiangliang Zhang, Richard Mccreadie, Idah Ounis.&nbsp;Jointly Learning Representations of Nodes and Attributes for Attributed Networks.&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3377850\">ACM Transactions on Information Systems (<strong>TOIS<\/strong>)<\/a>, 38(2), 1\u201332. 2020.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Peng Jia, Pinghui Wang, Yuchao Zhang, Xiangliang Zhang, Jing Tao, Jianwei Ding, Xiaohong Guan, Don Towsley.&nbsp;Accurately Estimating User Cardinalities and Detecting Super Spreaders over Time. &nbsp;<a rel=\"noreferrer noopener\" href=\"https:\/\/ieeexplore.ieee.org\/document\/9007395\" data-type=\"URL\" target=\"_blank\">IEEE Transactions on Knowledge and Data Engineering (<strong>TKDE<\/strong>)<\/a>, 2020\u200b.<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Mubashir Imran, Hongzhi Yin, Tong Chen, Yingxia Shao, Xiangliang Zhang, Xiaofang Zhou: Decentralized Embedding Framework for Large-Scale Networks.&nbsp;<a href=\"http:\/\/db.pknu.ac.kr\/dasfaa2020\/\">25th International Conference on Database Systems for Advanced Applications (DASFAA 2020)<\/a>, pp. &nbsp;425-441, Sep. 24-27, 2020, Jeju, South Korea (<strong>Best Student Paper Award<\/strong>).\u200b<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Uchenna\u200b&nbsp;Akujuobi, Qiannan Zhang, Han Yufei, Xiangliang Zhang. Recurrent Attention Walk for Semi-supervised Classification. In the proceedings of&nbsp;<a href=\"http:\/\/www.wsdm-conference.org\/2020\/\">The 13th ACM International <strong>WSDM<\/strong> Conference\u200b<\/a>. Feb 3-7, 2020, Houston, Texas. (Acceptance rate =91\/615 = 15%)\u200b&nbsp;(paper at&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/1910.10266\">arXiv<\/a>)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>\u200b\u200bYujun Chen, Ke Sun, Juhua Pu, Zhang Xiong, Xiangliang Zhang. GraPASA: Parametric Graph Embedding via Siamese Architecture. &nbsp;<a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0020025519309806\"><strong>Information Sciences<\/strong><\/a>&nbsp;512:&nbsp;1442-1457 (2020).\u200b\u200b\u200b<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Yujun Chen, Juhua Pu, Xingwu Liu, Xiangliang Zhang. Gaussian Mixture Embedding of Multiple Node Roles in Networks. &nbsp;<strong><a href=\"https:\/\/link.springer.com\/article\/10.1007\/s11280-019-00743-4\">World Wide Web<\/a><\/strong>&nbsp;23(2): 927-950 (2020)&nbsp;[<a href=\"https:\/\/drive.google.com\/file\/d\/1lI8Cbc8qqrrvFhxVk5qE_JjovETD9jmV\/view?usp=sharing\">PDF\u200b<\/a>]<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Uchenna Akujuobi, Han Yufei,&nbsp;Qiannan Zhang, Xiangliang Zhang.&nbsp;Collaborative Graph Walk for Semi-supervised Multi-Label Node Classification. In the proceedings of&nbsp;<a href=\"http:\/\/icdm2019.bigke.org\/\">19th IEEE International Conference on Data Mining&nbsp;(<strong>ICDM<\/strong> 2019)<\/a>,&nbsp;November 8-11, 2019,&nbsp;Beijing, China&nbsp;(Regular paper,&nbsp;Acceptance&nbsp;&nbsp;rate= 95\/1046 = 9.08%).\u200b&nbsp;(paper at&nbsp;arXiv\u200b)<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Basmah&nbsp;Altaf, Uchenna Akujuobi, Lu Yu, Xiangliang Zhang, Dataset Recommendation via Variational Graph Autoencoder. In the proceedings of&nbsp;<a href=\"http:\/\/icdm2019.bigke.org\/\">19th IEEE International Conference on Data Mining&nbsp;(<strong>ICDM<\/strong> 2019)<\/a>,&nbsp;November 8-11, 2019,&nbsp;Beijing, China&nbsp;(Regular&nbsp;paper,&nbsp;Acceptance rate= 95\/1046 = 9.08%).\u200b<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Yujun Chen, Yuanhong Wang, Yutao Zhang, Juhua Pu, &nbsp;Xiangliang Zhang. AMENDER: an Attentive and Aggregate Multi-layered Network for Dataset Recommendation. In the proceedings of&nbsp;<a href=\"http:\/\/icdm2019.bigke.org\/\">19th IEEE International Conference on Data Mining&nbsp;(<strong>ICDM <\/strong>2019)<\/a>,&nbsp;November 8-11, 2019,&nbsp;Beijing, China (Short paper, Acceptance rate= 18.5%).\u200b<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shichao Pei,&nbsp;Lu Yu,&nbsp;Xiangliang Zhang. Improving Cross-lingual Entity Alignment via Optimal Transport. In the proceedings of&nbsp;<a href=\"https:\/\/ijcai19.org\/\">28th International Joint Conference on Artificial Intelligence (<strong>IJCAI<\/strong> 2019)\u200b<\/a>, August 10-16, 2019, Macao, China (Acceptance rate=850\/4752=17.9%) [<a href=\"https:\/\/drive.google.com\/file\/d\/1x4xHzbCpkPD38Ufk3YQmiU__sFTen1Gj\/view?usp=sharing\">PDF<\/a>][Bib][<a href=\"https:\/\/drive.google.com\/file\/d\/1zexdABj27x7I1d33OUQN3my_t7Smt6OX\/view?usp=sharing\">Slides<\/a>].<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Xia Chen,&nbsp;Guoxian Yu, Jun Wang, Carlotta Domeniconi, Zhao Li,&nbsp;Xiangliang Zhang.&nbsp;ActiveHNE: Active Heterogeneous Network Embedding. In the proceedings of&nbsp;<a href=\"https:\/\/ijcai19.org\/\">28th International Joint Conference on Artificial Intelligence (<strong>IJCAI<\/strong> 2019)\u200b\u200b<\/a>,&nbsp;&nbsp;August 10-16, 2019, Macao, China. (Acceptance rate=850\/4752=17.9%).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shichao Pei, Lu Yu, Robert Hoehndorf,&nbsp;Xiangliang Zhang. Semi-Supervised Entity Alignment via Knowledge Graph Embedding with Awareness of Degree Difference.&nbsp; In the proceedings of&nbsp;by&nbsp;<a href=\"https:\/\/www2019.thewebconf.org\/\">TheWebConf 2019&nbsp;(previously known as&nbsp;<strong>WWW<\/strong> conference)<\/a>,&nbsp; May 13-17, San Francisco, CA, USA (short paper, acceptance rate ~&nbsp;20%) [<a href=\"https:\/\/drive.google.com\/file\/d\/1K490ponY7Ig0BRpGHQvGR0WhjqUVbG-4\/view?usp=sharing\">PDF<\/a>][Bib][<a href=\"https:\/\/drive.google.com\/file\/d\/1i0Oh8zBkecC5j1zHI0bgRF1Si0awcdfb\/view?usp=sharing\">Slides<\/a>\u200b][<a href=\"https:\/\/github.com\/scpei\/SEA\">Code<\/a>\u200b].<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Guolei Sun,&nbsp;Xiangliang Zhang. A Novel Framework for Node\/Edge Attributed Graph Embedding. In the proceedings of&nbsp;<a href=\"http:\/\/pakdd2019.medmeeting.org\/Content\/100312\">the 23rd&nbsp; Pacific-Asia Conference on Knowledge Discovery and Data Mining (<strong>PAKDD<\/strong> 2019),<\/a>&nbsp;14-17 April 2019, Macau SAR, China&nbsp;(regular paper, acceptance rate = 140\/567 =24.7%).<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Junzhou Zhao,&nbsp;Shuo Shang, Pinghui Wang, John C.S. Lui, and&nbsp;Xiangliang Zhang. Submodular Optimization Over Streams with Inhomogeneous Decays. In the proceedings of&nbsp;<a href=\"https:\/\/aaai.org\/Conferences\/AAAI-19\/\">the&nbsp;33rd AAAI Conference on Artificial Intelligence (<strong>AAAI<\/strong> 2019)<\/a>,&nbsp;January 27 \u2013 February 1, Honolulu, Hawaii, USA. (Acceptance rate = 1150\/7095&nbsp;=&nbsp;16.2%)&nbsp;[<a href=\"https:\/\/drive.google.com\/file\/d\/1ycfxdeIp81W0ashfvom73RF7v3yPMCin\/view?usp=sharing\">PDF<\/a><a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/papers\/walkranker_camera_ID749.pdf\">\u200b<\/a><a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/papers\/wraaaiv5.pdf\">\u200b<\/a>][Bib][Slides<a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/slides\/kdd2018_embeddings.pdf\">\u200b<\/a>].\u200b<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Zaiqiao Meng, Shangsong Liang,&nbsp;Hongyan Bao,&nbsp;and&nbsp;Xiangliang Zhang.&nbsp;Co-Embedding Attributed Networks. In the proceedings of&nbsp;<a href=\"http:\/\/www.wsdm-conference.org\/2019\/\">The Twelfth International Conference on Web Search and Data Mining (<strong>WSDM<\/strong> 2019)<\/a>,&nbsp;February \u200b11-15,&nbsp;2019,&nbsp;Melbourne, Australia&nbsp;&nbsp;(Acceptance rate = 84\/511 =&nbsp;16%)&nbsp;[<a href=\"https:\/\/drive.google.com\/file\/d\/10NTH4QSnV9AkCk-Gidqw35WQ6T0pbATF\/view?usp=sharing\">PDF\u200b\u200b<\/a>][Bib][Slides<a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/slides\/kdd2018_embeddings.pdf\">\u200b<\/a>][<a href=\"https:\/\/github.com\/mengzaiqiao\/CAN\">Code\u200b<\/a>].<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Junzhou Zhao, Shuo Shang, Pinghui Wang, John C.S. Lui, and&nbsp;Xiangliang Zhang: Tracking Influential Nodes in Time-Decaying Dynamic Interaction Networks. In the proceedings of&nbsp;the&nbsp;<a href=\"http:\/\/www.wsdm-conference.org\/2019\/\">35th IEEE International Conference on Data Engineering (<strong>ICDE<\/strong> 2019)<\/a>\u200b, 8-12 April 2019, Macau SAR, China [<a href=\"https:\/\/drive.google.com\/file\/d\/1lWYAOn0cQ_5BoYbhks3O871jg_BJT-u2\/view?usp=sharing\">PDF\u200b\u200b<\/a>][Bib][<a href=\"https:\/\/drive.google.com\/file\/d\/12YmL4UO5zhrgSRdPxvcXE_pUzqFdyexf\/view?usp=sharing\">Slides\u200b<\/a>].<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Pinghui Wang, Peng Jia,&nbsp;Xiangliang Zhang, Jing Tao, Xiaohong Guan, and Don Towsley: Utilizing Dynamic Properties of Sharing Bits and Registers&nbsp;to Estimate User Cardinalities over Time. In the proceedings of&nbsp;the&nbsp;<a href=\"http:\/\/www.wsdm-conference.org\/2019\/\">35th IEEE International Conference on Data Engineering (<strong>ICDE<\/strong> 2019)<\/a>\u200b, 8-12 April 2019, Macau SAR, China.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Uchenna Akujuobi, Ke Sun, and&nbsp;Xiangliang&nbsp;Zhang: &nbsp;Mining top-k Popular Datasets via a Deep Generative Model. In the proceedings of&nbsp; by<strong>&nbsp;<a href=\"http:\/\/cci.drexel.edu\/bigdata\/bigdata2018\/index.html\">IEEE Big Data<\/a><\/strong><a href=\"http:\/\/cci.drexel.edu\/bigdata\/bigdata2018\/index.html\"> 2018<\/a>,&nbsp;Seattle, WA, USA,&nbsp;December 10-13, 2018 (regular paper, acceptance rate = 98\/518 =18.9%)[<a href=\"https:\/\/drive.google.com\/file\/d\/1NS4kP_aL3haPfzVr_OmXJmjEXVkeZnIJ\/view?usp=sharing\">PDF\u200b<\/a>][Bib][Slides<a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/slides\/kdd2018_embeddings.pdf\">\u200b<\/a>].<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Shangsong Liang,&nbsp;Xiangliang&nbsp;Zhang, Zhaochun Ren and Evangelos Kanoulas:&nbsp;Dynamic Embeddings for User Profiling in Twitter. In Proceedings of the&nbsp;<a href=\"http:\/\/www.kdd.org\/kdd2018\/\">24th&nbsp;SIGKDD Conference on Knowledge Discovery and Data Mining (<strong>KDD <\/strong>2018)<\/a>,&nbsp;pp.&nbsp;1764-1773,&nbsp;London, UK,&nbsp;August 19 &#8211; 23, 2018&nbsp;(long presentation,&nbsp;acceptance rate= 107\/ 983 =10.9%)(overall acceptance rate=181\/983=18.4%)[PDF<a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/papers\/walkranker_camera_ID749.pdf\">\u200b<\/a><a href=\"https:\/\/mine.kaust.edu.sa\/Documents\/papers\/wraaaiv5.pdf\">\u200b<\/a>][Bib][<a href=\"https:\/\/drive.google.com\/file\/d\/1TXw_HGCv4f0YevfM2kQ6DirrQww5vRpQ\/view?usp=sharing\">Slides\u200b<\/a>]\u200b\u200b.<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Pinghui Wang, Yiyan Qi, Yu Sun,&nbsp;Xiangliang Zhang, Jing Tao, Xiaohong Guan.&nbsp;Approximately Counting Triangles in Large Graph Streams Including Edge Duplicates with a Fixed Memory Usage. In Proceedings of&nbsp;&nbsp;Very Large Data Bases&nbsp;(<strong>VLDB<\/strong> 2017),&nbsp;11(2): 162-175, 2017&nbsp;[PDF][Bib].\u200b<\/li>\n<\/ul>\n\n\n\n<ul id=\"block-0d72bc55-c2e9-48c8-a073-d13639c852dd\" class=\"wp-block-list\">\n<li>Pinghui Wang, Junzhou Zhao,&nbsp;Xiangliang Zhang, Zhenguo Li, Jiefeng Cheng, John C.S. Lui, Don Towsley, Jing Tao, Xiaohong Guan.&nbsp;MOSS-5: A Fast Method of Approximating Counts of 5-Node Graphlets in Large Graphs. In&nbsp;<a href=\"http:\/\/www.computer.org\/tkde\">IEEE Transactions on Knowledge and Data Engineering (<strong>TKDE<\/strong>)\u200b<\/a>,&nbsp;30(1): 73-86,&nbsp;2017.\u200b<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We design machine learning models for solving diverse graph\/network problems, such as attributed network embedding, knowledge graph alignment, knowledge graph completion, dynamic graph modeling, spatial-temporal network embedding and influential nodes tracking in dynamic networks.<\/p>\n","protected":false},"author":4036,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-108","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/pages\/108","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/users\/4036"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/comments?post=108"}],"version-history":[{"count":43,"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/pages\/108\/revisions"}],"predecessor-version":[{"id":1581,"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/pages\/108\/revisions\/1581"}],"wp:attachment":[{"href":"https:\/\/sites.nd.edu\/xiangliang-zhang\/wp-json\/wp\/v2\/media?parent=108"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}