{"type":"ScholarlyArticle","title":"Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning","authors":[{"name":"Honglu Zhou","slug":"honglu-zhou","given":"Honglu","family":"Zhou","affiliation":"Rutgers University , Department of Computer Science , Piscataway , NJ , US"},{"name":"Advith Chegu","slug":"advith-chegu","given":"Advith","family":"Chegu","affiliation":"Rutgers University , Department of Computer Science , Piscataway , NJ , US"},{"name":"Samuel S. Sohn","slug":"samuel-s-sohn","given":"Samuel S.","family":"Sohn","affiliation":"Rutgers University , Department of Computer Science , Piscataway , NJ , US"},{"name":"Zuohui Fu","slug":"zuohui-fu","given":"Zuohui","family":"Fu","affiliation":"Rutgers University , Department of Computer Science , Piscataway , NJ , US"},{"name":"Gerard de Melo","slug":"gerard-de-melo","given":"Gerard","family":"de Melo","affiliation":"HPI / University of Potsdam , Potsdam , Germany"},{"name":"Mubbasir Kapadia","slug":"mubbasir-kapadia","given":"Mubbasir","family":"Kapadia","affiliation":"Rutgers University , Department of Computer Science , Piscataway , NJ , US"}],"abstract":"Digraph Representation Learning aims to learn representations for directed homogeneous graphs (digraphs). Prior work is largely constrained or has poor generalizability across tasks. Most Graph Neural Networks exhibit poor performance on digraphs due to the neglect of modeling neighborhoods and preserving asymmetry. In this paper, we address these notable challenges by leveraging hyperbolic collaborative learning from multi-ordered partitioned neighborhoods and asymmetry-preserving regularizers. Our resulting formalism, Digraph Hyperbolic Networks (D-HYPR), is versatile for multiple tasks including node classification, link presence prediction, and link property prediction. The efficacy of D-HYPR was meticulously examined against 21 previous techniques, using 8 real-world digraph datasets. D-HYPR statistically significantly outperforms the current state of the art. We release our code at https://github. com/hongluzhou/dhypr.","doi":"10.24963/ijcai.2023/731","url":"https://ijcai.org/proceedings/2023/731","pdf":"https://ijcai.org/proceedings/2023/0731.pdf","markdown":"https://ijcai.org/proceedings/2023/731.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/731","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":731,"pages":{"first":6519,"last":6524},"keywords":["Sister Conferences Best Papers: Machine Learning","Sister Conferences Best Papers: Data Mining","Sister Conferences Best Papers: Knowledge Representation and Reasoning"],"videos":[],"references":[{"position":1,"raw":"[Chami et al., 2019] Ines Chami, Zhitao Ying, Christopher Ré, and Jure Leskovec. Hyperbolic graph convolutional neural networks. In Advances in neural information pro- cessing systems, pages 4868-4879, 2019.","title":"Hyperbolic graph convolutional neural networks","authors":"Ines Chami, Zhitao Ying, Christopher Ré, Jure Leskovec","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ganea et al., 2018] Octavian Ganea, Gary Bécigneul, and Thomas Hofmann. Hyperbolic neural networks. In Ad- vances in neural information processing systems, pages 5345-5355, 2018.","title":"Hyperbolic neural networks","authors":"Ganea","year":"2018","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gong and Cheng, 2019] Liyu Gong and Qiang Cheng. Ex- ploiting edge features for graph neural networks. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9211-9219, 2019.","title":"Exploiting edge features for graph neural networks","authors":"Cheng ; ] Liyu Gong, Qiang Gong, Cheng","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Grover and Leskovec, 2016] Aditya Grover and Jure Leskovec. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 855-864, 2016.","title":"node2vec: Scalable feature learning for networks","authors":"Leskovec Grover, Aditya Grover, Jure Leskovec","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Khosla et al., 2019] Megha Khosla, Jurek Leonhardt, Wolf- gang Nejdl, and Avishek Anand. Node representation learning for directed graphs. In Joint European Confer- ence on Machine Learning and Knowledge Discovery in Databases, pages 395-411. Springer, 2019.","title":"Node representation learning for directed graphs","authors":"Megha Khosla, Jurek Leonhardt, Wolfgang Nejdl, Avishek Anand","year":"2019","venue":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kipf and Welling, 2016a] Thomas N Kipf and Max Welling. Semi-supervised classification with graph con- volutional networks. arXiv preprint arXiv:1609.02907, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"Welling ; Kipf, N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kipf and Welling, 2016b] Thomas N Kipf and Max Welling. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308, 2016.","title":"Variational graph auto-encoders","authors":"Welling ; Kipf, N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Krioukov et al., 2010] Dmitri Krioukov, Fragkiskos Pa- padopoulos, Maksim Kitsak, Amin Vahdat, and Marián Boguná. Hyperbolic geometry of complex networks. Physical Review E, 82(3):036106, 2010.","title":"Hyperbolic geometry of complex networks","authors":"Dmitri Krioukov, Fragkiskos Papadopoulos, Maksim Kitsak, Amin Vahdat, Marián Boguná","year":"2010","venue":"Physical Review E","doi":null,"url":null,"internal_url":null},{"position":9,"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":10,"raw":"[McPherson et al., 2001] Miller McPherson, Lynn Smith- Lovin, and James M Cook. Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1):415- 444, 2001.","title":"Birds of a feather: Homophily in social networks","authors":"Mcpherson","year":"2001","venue":"Annual review of sociology","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mitzenmacher, 2004] Michael Mitzenmacher. A brief his- tory of generative models for power law and lognormal distributions. Internet mathematics, 1(2):226-251, 2004.","title":"A brief history of generative models for power law and lognormal distributions","authors":"Michael Mitzenmacher","year":"2004","venue":"Internet mathematics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ou et al., 2016] Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, and Wenwu Zhu. Asymmetric transitivity preserv- ing graph embedding. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discov- ery and data mining, pages 1105-1114, 2016.","title":"Asymmetric transitivity preserving graph embedding","authors":"Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, Wenwu Zhu","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Salha et al., 2019] Guillaume Salha, Stratis Limnios, Ro- main Hennequin, Viet-Anh Tran, and Michalis Vazirgian- nis. Gravity-inspired graph autoencoders for directed link prediction. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pages 589-598, 2019.","title":"Gravity-inspired graph autoencoders for directed link prediction","authors":"Guillaume Salha, Stratis Limnios, Romain Hennequin, Michalis Viet-Anh Tran, Vazirgiannis","year":"2019","venue":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shi et al., 2019] Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. Skeleton-based action recognition with di- rected graph neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7912-7921, 2019.","title":"Skeleton-based action recognition with directed graph neural networks","authors":"Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sim et al., 2021] Aaron Sim, Maciej L Wiatrak, Angus Brayne, Páidí Creed, and Saee Paliwal. Directed graph embeddings in pseudo-riemannian manifolds. In Inter- national Conference on Machine Learning, pages 9681- 9690. PMLR, 2021.","title":"Directed graph embeddings in pseudo-riemannian manifolds","authors":"Aaron Sim, L Maciej, Angus Wiatrak, Páidí Brayne, Saee Creed, Paliwal","year":"2021","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Sun et al., 2019] Jiankai Sun, Bortik Bandyopadhyay, Armin Bashizade, Jiongqian Liang, P Sadayappan, and Srinivasan Parthasarathy. Atp: Directed graph embedding with asymmetric transitivity preservation. In Proceed- ings of the AAAI Conference on Artificial Intelligence, volume 33, pages 265-272, 2019.","title":"Atp: Directed graph embedding with asymmetric transitivity preservation","authors":"Sun","year":"2019","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Thost and Chen, 2021] Veronika Thost and Jie Chen. Di- rected acyclic graph neural networks. International Con- ference on Learning Representations, 2021.","title":"Directed acyclic graph neural networks","authors":"Veronika Thost, Jie Chen","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tong et al., 2020a] Zekun Tong, Yuxuan Liang, Chang- sheng Sun, Xinke Li, David Rosenblum, and Andrew Lim. Digraph inception convolutional networks. Advances in Neural Information Processing Systems, 33, 2020.","title":"Digraph inception convolutional networks","authors":"Tong","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"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":20,"raw":"[Veličković et al., 2017] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhang et al., 2021a] Xitong Zhang, Nathan Brugnone, Michael Perlmutter, and Matthew Hirn. Magnet: A mag- netic neural network for directed graphs. Advances in Neu- ral Information Processing Systems, 34, 2021.","title":"Magnet: A magnetic neural network for directed graphs","authors":"Zhang","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2021b] Yiding Zhang, Xiao Wang, Chuan Shi, Xunqiang Jiang, and Yanfang Fanny Ye. Hyperbolic graph attention network. IEEE Transactions on Big Data, 2021.","title":"Hyperbolic graph attention network","authors":"Zhang","year":"2021","venue":"IEEE Transactions on Big Data","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhou et al., 2017] Chang Zhou, Yuqiong Liu, Xiaofei Liu, Zhongyi Liu, and Jun Gao. Scalable graph embedding for asymmetric proximity. In Proceedings of the AAAI Con- ference on Artificial Intelligence, volume 31, 2017.","title":"Scalable graph embedding for asymmetric proximity","authors":"Chang Zhou, Yuqiong Liu, Xiaofei Liu, Zhongyi Liu, Jun Gao","year":"2017","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhou et al., 2020] Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. Graph neural networks: A review of methods and applications. AI Open, 1:57-81, 2020.","title":"Graph neural networks: A review of methods and applications","authors":"Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun","year":"2020","venue":"AI Open","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhou et al., 2022] Honglu Zhou, Advith Chegu, Samuel S Sohn, Zuohui Fu, Gerard De Melo, and Mubbasir Ka- padia. D-hypr: Harnessing neighborhood modeling and asymmetry preservation for digraph representation learn- ing. In Proceedings of the 31st ACM International Con- ference on Information & Knowledge Management, pages 2732-2742, 2022.","title":"D-hypr: Harnessing neighborhood modeling and asymmetry preservation for digraph representation learning","authors":"Zhou","year":"2022","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhu et al., 2020] Shichao Zhu, Shirui Pan, Chuan Zhou, Jia Wu, Yanan Cao, and Bin Wang. Graph geometry interac- tion learning. In Advances in Neural Information Process- ing Systems, 2020.","title":"Graph geometry interaction learning","authors":"Zhu","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."}