{"type":"ScholarlyArticle","title":"Exploring the Role of Node Diversity in Directed Graph Representation Learning","authors":[{"name":"Jincheng Huang","slug":"jincheng-huang","given":"Jincheng","family":"Huang","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Yujie Mo","slug":"yujie-mo","given":"Yujie","family":"Mo","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Ping Hu","slug":"ping-hu","given":"Ping","family":"Hu","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Xiaoshuang Shi","slug":"xiaoshuang-shi","given":"Xiaoshuang","family":"Shi","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Shangbo Yuan","slug":"shangbo-yuan","given":"Shangbo","family":"Yuan","affiliation":"School of Engineering and Design , Technical University of Munich"},{"name":"Zeyu Zhang","slug":"zeyu-zhang","given":"Zeyu","family":"Zhang","affiliation":"Huazhong Agricultural University"},{"name":"Xiaofeng Zhu","slug":"xiaofeng-zhu","given":"Xiaofeng","family":"Zhu","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"}],"abstract":"Many methods of Directed Graph Neural Networks (DGNNs) are designed to equally treat nodes in the same neighbor set (i.e., out-neighbor set and in-neighbor set) for every node, without considering the node diversity in directed graphs, so they are often unavailable to adaptively acquire suitable information from neighbors of different directions. To alleviate this issue, in this paper, we investigate a new way to first consider node diversity for representation learning on directed graphs, i.e., neighbor diversity and degree diversity, and then propose a new NDDGNN framework to adaptively assign weights to both outgoing information and incoming information at the node level. Extensive experiments on seven real-world datasets validate the superior performance of our method compared to state-of-the-art methods in terms of both node classification and link prediction tasks.","doi":"10.24963/ijcai.2024/229","url":"https://ijcai.org/proceedings/2024/229","pdf":"https://ijcai.org/proceedings/2024/0229.pdf","markdown":"https://ijcai.org/proceedings/2024/229.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/229","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Data Mining","track":"Main Track","number":229,"pages":{"first":2072,"last":2080},"keywords":["Machine Learning: ML: Semi-supervised learning","Machine Learning: ML: Representation learning","Data Mining: DM: Mining graphs"],"videos":[],"references":[{"position":1,"raw":"[Bi et al., 2022a] Wendong Bi, Lun Du, Qiang Fu, Yanlin Wang, Shi Han, and Dongmei Zhang. Make heterophily graphs better fit gnn: A graph rewiring approach. arXiv preprint arXiv:2209.08264, 2022.","title":"Make heterophily graphs better fit gnn: A graph rewiring approach","authors":"Bi","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bi et al., 2022b] Wendong Bi, Bingbing Xu, Xiaoqian Sun, Zidong Wang, Huawei Shen, and Xueqi Cheng. Company- as-tribe: Company financial risk assessment on tribe-style graph with hierarchical graph neural networks. In Pro- ceedings of the 28th ACM SIGKDD Conference on Knowl- edge Discovery and Data Mining, pages 2712-2720, 2022.","title":"Companyas-tribe: Company financial risk assessment on tribe-style graph with hierarchical graph neural networks","authors":"Bi","year":"2022","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bi et al., 2023] Wendong Bi, Lun Du, Qiang Fu, Yanlin Wang, Shi Han, and Dongmei Zhang. Mm-gnn: Mix- moment graph neural network towards modeling neigh- borhood feature distribution. In ACM International Con- ference on Web Search and Data Mining(WSDM), pages 132-140, 2023.","title":"Mm-gnn: Mixmoment graph neural network towards modeling neighborhood feature distribution","authors":"Wendong Bi, Lun Du, Qiang Fu, Yanlin Wang, Shi Han, Dongmei Zhang","year":"2023","venue":"ACM International Conference on Web Search and Data Mining(WSDM)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bojchevski and Günnemann, 2018] Aleksandar Bojchevski and Stephan Günnemann. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. In International Conference on Learning Representations, (ICLR). OpenReview.net, 2018.","title":"Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking","authors":"Aleksandar Bojchevski, Stephan Günnemann","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Brin, 1998] Sergey Brin. The pagerank citation ranking: bringing order to the web. volume 98, pages 161-172, 1998.","title":"The pagerank citation ranking: bringing order to the web","authors":"Sergey Brin, Brin","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chien et al., 2021] Eli Chien, Jianhao Peng, Pan Li, and Ol- gica Milenkovic. Adaptive universal generalized pager- ank graph neural network. In International Conference on Learning Representations, (ICLR). OpenReview.net, 2021.","title":"Adaptive universal generalized pagerank graph neural network","authors":"Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Du et al., 2022] Lun Du, Xiaozhou Shi, Qiang Fu, Xiaojun Ma, Hengyu Liu, Shi Han, and Dongmei Zhang. Gbk- gnn: Gated bi-kernel graph neural networks for modeling both homophily and heterophily. In ACM Web Conference, pages 1550-1558, 2022.","title":"Gbkgnn: Gated bi-kernel graph neural networks for modeling both homophily and heterophily","authors":"Lun Du, Xiaozhou Shi, Qiang Fu, Xiaojun Ma, Hengyu Liu, Shi Han, Dongmei Zhang","year":"2022","venue":"ACM Web Conference","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hamilton et al., 2017] William L Hamilton, Rex Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Advances in neural information processing sys- tems(Neurips), pages 1025-1035, 2017.","title":"Inductive representation learning on large graphs","authors":"Rex William L Hamilton, Jure Ying, Leskovec","year":"2017","venue":"Advances in neural information processing systems(Neurips)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2023a] Jincheng Huang, Lun Du, Xu Chen, Qiang Fu, Shi Han, and Dongmei Zhang. Robust mid- pass filtering graph convolutional networks. In ACM Web Conference(WWW), pages 328-338, 2023.","title":"Robust midpass filtering graph convolutional networks","authors":"Huang","year":"2023","venue":"ACM Web Conference(WWW)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2023b] Jincheng Huang, Ping Li, Rui Huang, Na Chen, and Acong Zhang. Revisiting the role of het- erophily in graph representation learning: An edge clas- sification perspective. ACM Transactions on Knowledge Discovery from Data, 2023.","title":"Revisiting the role of heterophily in graph representation learning: An edge classification perspective","authors":"Huang","year":"2023","venue":"ACM Transactions on Knowledge Discovery from Data","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors, International Confer- ence on Learning Representations(ICLR), 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"International Conference on Learning Representations(ICLR)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kipf and Welling, 2017] Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Rep- resentations, (ICLR), 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"Thomas N Kipf, Max Welling","year":"2017","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Leskovec and Krevl, 2014] Jure Leskovec and Andrej Krevl. Snap datasets: Stanford large network dataset collection, 2014.","title":"Snap datasets: Stanford large network dataset collection","authors":"Jure Leskovec, Andrej Krevl","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Leskovec et al., 2005] Jure Leskovec, Jon Kleinberg, and Christos Faloutsos. Graphs over time: densification laws, shrinking diameters and possible explanations. In ACM International conference on Knowledge discovery in data mining(SIGKDD), pages 177-187, 2005.","title":"Graphs over time: densification laws, shrinking diameters and possible explanations","authors":"Jure Leskovec, Jon Kleinberg, Christos Faloutsos","year":"2005","venue":"ACM International conference on Knowledge discovery in data mining(SIGKDD)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2022] Xiang Li, Renyu Zhu, Yao Cheng, Caihua Shan, Siqiang Luo, Dongsheng Li, and Weining Qian. Finding global homophily in graph neural networks when meeting heterophily. In International Conference on Machine Learning(ICML), pages 13242-13256. PMLR, 2022.","title":"Finding global homophily in graph neural networks when meeting heterophily","authors":"Xiang Li, Renyu Zhu, Yao Cheng, Caihua Shan, Siqiang Luo, Dongsheng Li, Weining Qian","year":"2022","venue":"International Conference on Machine Learning(ICML)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lim et al., 2021] Derek Lim, Felix Hohne, Xiuyu Li, Si- jia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, and Ser Nam Lim. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. vol- ume 34, pages 20887-20902, 2021.","title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","authors":"Derek Lim, Felix Hohne, Xiuyu Li, Linda Sijia, Vaishnavi Huang, Omkar Gupta, Bhalerao, Nam Ser, Lim","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Luan et al., 2022] Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, and Doina Precup. Revisiting heterophily for graph neural networks. Advances in neural information processing systems(Neurips), 35:1362-1375, 2022.","title":"Revisiting heterophily for graph neural networks","authors":"Luan","year":"2022","venue":"Advances in neural information processing systems(Neurips)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ma et al., 2019] Yi Ma, Jianye Hao, Yaodong Yang, Han Li, Junqi Jin, and Guangyong Chen. Spectral-based graph convolutional network for directed graphs. arXiv preprint arXiv:1907.08990, 2019.","title":"Spectral-based graph convolutional network for directed graphs","authors":"Yi Ma, Jianye Hao, Yaodong Yang, Han Li, Junqi Jin, Guangyong Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Maurya et al., 2021] Sunil Kumar Maurya, Xin Liu, and Tsuyoshi Murata. Improving graph neural networks with simple architecture design. arXiv preprint arXiv:2105.07634, 2021.","title":"Improving graph neural networks with simple architecture design","authors":"Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mo et al., 2023] Yujie Mo, Yajie Lei, Jialie Shen, Xi- aoshuang Shi, Heng Tao Shen, and Xiaofeng Zhu. Disen- tangled multiplex graph representation learning. In ICML, volume 202, pages 24983-25005, 2023.","title":"Disentangled multiplex graph representation learning","authors":"Yujie Mo, Yajie Lei, Jialie Shen, Xiaoshuang Shi, Heng Tao Shen, Xiaofeng Zhu","year":"2023","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mo et al., 2024] Yujie Mo, Feiping Nie, Ping Hu, Heng Tao Shen, Zheng Zhang, Xinchao Wang, and Xiaofeng Zhu. Self-supervised heterogeneous graph learning: a ho- mophily and heterogeneity view. In ICLR, 2024.","title":"Self-supervised heterogeneous graph learning: a homophily and heterogeneity view","authors":"Yujie Mo, Feiping Nie, Ping Hu, Heng Tao Shen, Zheng Zhang, Xinchao Wang, Xiaofeng Zhu","year":"2024","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Monti et al., 2018] Federico Monti, Karl Otness, and Michael M Bronstein. Motifnet: a motif-based graph convolutional network for directed graphs. In 2018 IEEE Data Science Workshop(DSW), pages 225-228, 2018.","title":"Motifnet: a motif-based graph convolutional network for directed graphs","authors":"Federico Monti, Karl Otness, Michael M Bronstein","year":"2018","venue":"IEEE Data Science Workshop(DSW)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pei et al., 2020] Hongbin Pei, Bingzhe Wei, Kevin Chen- Chuan Chang, Yu Lei, and Bo Yang. Geom-gcn: Ge- ometric graph convolutional networks. In International Conference on Learning Representations, (ICLR). Open- Review.net, 2020.","title":"Geom-gcn: Geometric graph convolutional networks","authors":"Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan, Yu Chang, Bo Lei, Yang","year":"2020","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Platonov et al., 2023] Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, and Liudmila Prokhorenkova. A critical look at the evaluation of gnns under heterophily: are we really making progress? arXiv preprint arXiv:2302.11640, 2023.","title":"A critical look at the evaluation of gnns under heterophily: are we really making progress","authors":"Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, Liudmila Prokhorenkova","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Rossi et al., 2023] Emanuele Rossi, Bertrand Charpen- tier, Francesco Di Giovanni, Fabrizio Frasca, Stephan Günnemann, and Michael M. Bronstein. Edge directional- ity improves learning on heterophilic graphs. In The Sec- ond Learning on Graphs Conference(LOG), 2023.","title":"Edge directionality improves learning on heterophilic graphs","authors":"Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni, Fabrizio Frasca, Stephan Günnemann, Michael M Bronstein","year":"2023","venue":"The Second Learning on Graphs Conference(LOG)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Rusch et al., 2023] T. Konstantin Rusch, Benjamin Paul Chamberlain, Michael W. Mahoney, Michael M. Bron- stein, and Siddhartha Mishra. Gradient gating for deep multi-rate learning on graphs. In International Conference on Learning Representations, (ICLR). OpenReview.net, 2023.","title":"Gradient gating for deep multi-rate learning on graphs","authors":"T, Konstantin Rusch, Benjamin Paul Chamberlain, Michael W Mahoney, Michael M Bronstein, Siddhartha Mishra","year":"2023","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tong et al., 2020a] Zekun Tong, Yuxuan Liang, Chang- sheng Sun, Xinke Li, David Rosenblum, and Andrew Lim. Digraph inception convolutional networks. Ad- vances in neural information processing systems(Neurips), 33:17907-17918, 2020.","title":"Digraph inception convolutional networks. Advances in neural information processing systems","authors":"Tong","year":"2020","venue":"Neurips)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tong et al., 2020b] Zekun Tong, Yuxuan Liang, Chang- sheng Sun, David S Rosenblum, and Andrew Lim. Di- rected graph convolutional network. arXiv preprint arXiv:2004.13970, 2020.","title":"Directed graph convolutional network","authors":"Tong","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Tong et al., 2021] Zekun Tong, Yuxuan Liang, Henghui Ding, Yongxing Dai, Xinke Li, and Changhu Wang. Di- rected graph contrastive learning. Advances in neural in- formation processing systems(Neurips), 34:19580-19593, 2021.","title":"Directed graph contrastive learning","authors":"Tong","year":"2021","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Velickovic et al., 2018] Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In Interna- tional Conference on Learning Representations, (ICLR). OpenReview.net, 2018.","title":"Graph attention networks","authors":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Xu et al., 2023] Lei Xu, Lei Chen, Rong Wang, Feiping Nie, and Xuelong Li. Joint feature and differentiable k- nn graph learning using dirichlet energy. arXiv preprint arXiv:2305.12396, 2023.","title":"Joint feature and differentiable knn graph learning using dirichlet energy","authors":"Lei Xu, Lei Chen, Rong Wang, Feiping Nie, Xuelong Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yang et al., 2023a] Xihong Yang, Yue Liu, Sihang Zhou, Si- wei Wang, Wenxuan Tu, Qun Zheng, Xinwang Liu, Lim- ing Fang, and En Zhu. Cluster-guided contrastive graph clustering network. In Proceedings of the AAAI confer- ence on artificial intelligence (AAAI), volume 37, pages 10834-10842, 2023.","title":"Cluster-guided contrastive graph clustering network","authors":"Yang","year":"2023","venue":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yang et al., 2023b] Xihong Yang, Cheng Tan, Yue Liu, Ke Liang, Siwei Wang, Sihang Zhou, Jun Xia, Stan Z Li, Xinwang Liu, and En Zhu. Convert: Contrastive graph clustering with reliable augmentation. In Proceedings of the 31st ACM International Conference on Multimedia (MM), pages 319-327, 2023.","title":"Convert: Contrastive graph clustering with reliable augmentation","authors":"Yang","year":"2023","venue":"Proceedings of the 31st ACM International Conference on Multimedia (MM)","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang et al., 2021] Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, and Matthew Hirn. Mag- net: A neural network for directed graphs. Ad- vances in neural information processing systems(Neurips), 34:27003-27015, 2021.","title":"Mag-net: A neural network for directed graphs","authors":"Zhang","year":"2021","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhu et al., 2020] Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. Be- yond homophily in graph neural networks: Current limita- tions and effective designs. In Advances in neural infor- mation processing systems(Neurips), 2020.","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","authors":"Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}