ABSTRACT
Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space, leading to the information loss of topological properties (e.g. hierarchy and circularity). Moreover, due to the topological heterogeneity (i.e., different densities across the graph structure) of graph data, they suffer from serious topological distortion problems. In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. To better preserve the topological properties, we approximate the discrete structure as a continuous Riemannian geometric manifold and generate negative samples efficiently from the wrapped normal distribution. To deal with the topological heterogeneity, we leverage the Ricci curvature for local structures with different topological properties, obtaining to low-distortion representations. Extensive experiments show that CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks and shows superior robustness and generalization.
- Lada A Adamic and Natalie Glance. 2005. The political blogosphere and the 2004 US election: divided they blog. In LinkKDD. 36–43.Google Scholar
- Stephanie Alexander. 1978. Michael Spivak, A comprehensive introduction to differential geometry. Bull. Amer. Math. Soc. 84, 1 (1978), 27–32.Google ScholarCross Ref
- Gregor Bachmann, Gary Bécigneul, and Octavian Ganea. 2020. Constant curvature graph convolutional networks. In ICML. PMLR, 486–496.Google Scholar
- Albert-László Barabási and Réka Albert. 1999. Emergence of scaling in random networks. Science 286, 5439 (1999), 509–512.Google Scholar
- Marian Boguna, Ivan Bonamassa, Manlio De Domenico, Shlomo Havlin, Dmitri Krioukov, and M Ángeles Serrano. 2021. Network geometry. Nature Reviews Physics 3, 2 (2021), 114–135.Google ScholarCross Ref
- Aleksandar Bojchevski and Stephan Günnemann. 2018. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking. In ICLR.Google Scholar
- Michael M Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. 2017. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine 34, 4 (2017), 18–42.Google ScholarCross Ref
- Lawrence Cayton. 2005. Algorithms for manifold learning. Univ. of California at San Diego Tech. Rep 12, 1-17 (2005), 1.Google Scholar
- Ines Chami, Zhitao Ying, Christopher Ré, and Jure Leskovec. 2019. Hyperbolic Graph Convolutional Neural Networks. In NeurIPS. 4869–4880.Google Scholar
- Quanyu Dai, Qiang Li, Jian Tang, and Dan Wang. 2018. Adversarial network embedding. In AAAI. 2167–2174.Google Scholar
- Tim R Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, and Jakub M Tomczak. 2018. Hyperspherical variational auto-encoders. UAI (2018).Google Scholar
- Michaël Defferrard, Nathanaël Perraudin, Tomasz Kacprzak, and Raphael Sgier. 2019. Deepsphere: towards an equivariant graph-based spherical cnn. ICLR (2019).Google Scholar
- Xingcheng Fu, Jianxin Li, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Jiajun Tan, Hao Peng, and S Yu Philip. 2021. ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network. In ICDM. IEEE, 111–120.Google Scholar
- Octavian-Eugen Ganea, Gary Bécigneul, and Thomas Hofmann. 2018. Hyperbolic Neural Networks. In NeurIPS, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett (Eds.). 5350–5360.Google Scholar
- Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In ICML. 1263–1272.Google Scholar
- Michelle Girvan and Mark EJ Newman. 2002. Community structure in social and biological networks. national academy of sciences 99, 12 (2002), 7821–7826.Google Scholar
- Daniele Grattarola, Lorenzo Livi, and Cesare Alippi. 2019. Adversarial autoencoders with constant-curvature latent manifolds. Applied Soft Computing 81 (2019), 105511.Google ScholarDigital Library
- Daniele Grattarola, Daniele Zambon, Cesare Alippi, and Lorenzo Livi. 2018. Learning graph embeddings on constant-curvature manifolds for change detection in graph streams. STAT 1050(2018), 16.Google Scholar
- Albert Gu, Frederic Sala, Beliz Gunel, and Christopher Ré. 2019. Learning mixed-curvature representations in product spaces. In ICLR.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS. 1024–1034.Google Scholar
- Paul W Holland, Kathryn Blackmond Laskey, and Samuel Leinhardt. 1983. Stochastic blockmodels: First steps. Social networks 5, 2 (1983), 109–137.Google Scholar
- Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. In NeurIPS.Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.Google Scholar
- Dmitri Krioukov, Fragkiskos Papadopoulos, Maksim Kitsak, Amin Vahdat, and Marián Boguná. 2010. Hyperbolic geometry of complex networks. Physical Review E 82, 3 (2010), 036106.Google ScholarCross Ref
- Jianxin Li, Xingcheng Fu, Hao Peng, Senzhang Wang, Shijie Zhu, Qingyun Sun, Philip S Yu, and Lifang He. 2021. A Robust and Generalized Framework for Adversarial Graph Embedding. arXiv preprint arXiv:2105.10651(2021).Google Scholar
- Yaxin Li, Wei Jin, Han Xu, and Jiliang Tang. 2021. Deeprobust: A pytorch library for adversarial attacks and defenses. In AAAI.Google Scholar
- Tong Lin and Hongbin Zha. 2008. Riemannian manifold learning. IEEE transactions on pattern analysis and machine intelligence 30, 5(2008), 796–809.Google Scholar
- Yong Lin, Linyuan Lu, and Shing-Tung Yau. 2011. Ricci curvature of graphs. Tohoku Mathematical Journal, Second Series 63, 4 (2011), 605–627.Google ScholarCross Ref
- Fanzhen Liu, Shan Xue, Jia Wu, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Jian Yang, and Philip S. Yu. 2020. Deep Learning for Community Detection: Progress, Challenges and Opportunities. In IJCAI. 4981––4987.Google Scholar
- Xiaomei Liu, Suqin Tang, and Jinyan Wang. 2018. Generative Adversarial Graph Representation Learning in Hyperbolic Space. In CCIR. 119–131.Google Scholar
- Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z Sheng, Hui Xiong, and Leman Akoglu. 2021. A comprehensive survey on graph anomaly detection with deep learning. IEEE Transactions on Knowledge and Data Engineering (2021).Google ScholarDigital Library
- Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, and Yee Whye Teh. 2019. Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders. In NeurIPS.Google Scholar
- Ujjwal Maulik, Lawrence B Holder, and Diane J Cook. 2006. Advanced methods for knowledge discovery from complex data. Springer Science & Business Media.Google Scholar
- Yoshihiro Nagano, Shoichiro Yamaguchi, Yasuhiro Fujita, and Masanori Koyama. 2019. A differentiable gaussian-like distribution on hyperbolic space for gradient-based learning. In ICML.Google Scholar
- Hariharan Narayanan and Sanjoy Mitter. 2010. Sample complexity of testing the manifold hypothesis. In NeurIPS. 1786–1794.Google Scholar
- Chien-Chun Ni, Yu-Yao Lin, Jie Gao, Xianfeng David Gu, and Emil Saucan. 2015. Ricci curvature of the internet topology. In INFOCOM. IEEE, 2758–2766.Google Scholar
- Maximilian Nickel and Douwe Kiela. 2017. Poincaré Embeddings for Learning Hierarchical Representations. In NeurIPS. 6338–6347.Google Scholar
- Yann Ollivier. 2009. Ricci curvature of Markov chains on metric spaces. Journal of Functional Analysis 256, 3 (2009), 810–864.Google ScholarCross Ref
- Fragkiskos Papadopoulos, Maksim Kitsak, M Ángeles Serrano, Marián Boguná, and Dmitri Krioukov. 2012. Popularity versus similarity in growing networks. Nature (2012), 537–540.Google Scholar
- Hao Peng, Ruitong Zhang, Yingtong Dou, Renyu Yang, Jingyi Zhang, and Philip S Yu. 2021. Reinforced neighborhood selection guided multi-relational graph neural networks. ACM Transactions on Information Systems (TOIS) 40, 4 (2021), 1–46.Google ScholarDigital Library
- 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).Google ScholarCross Ref
- Salah Rifai, Yann N Dauphin, Pascal Vincent, Yoshua Bengio, and Xavier Muller. 2011. The manifold tangent classifier. In NeurIPS, Vol. 24. 2294–2302.Google Scholar
- Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine 29, 3 (2008), 93–93.Google Scholar
- Jayson Sia, Edmond Jonckheere, and Paul Bogdan. 2019. Ollivier-ricci curvature-based method to community detection in complex networks. Scientific reports 9, 1 (2019), 1–12.Google Scholar
- Ondrej Skopek, Octavian-Eugen Ganea, and Gary Bécigneul. 2020. Mixed-curvature Variational Autoencoders. In ICLR.Google Scholar
- Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cécile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, and Philip S. Yu. 2021. A Comprehensive Survey on Community Detection with Deep Learning. CoRR abs/2105.12584(2021).Google Scholar
- Li Sun, Zhongbao Zhang, Junda Ye, Hao Peng, Jiawei Zhang, Sen Su, and Philip S Yu. 2021. A Self-supervised Mixed-curvature Graph Neural Network. arXiv preprint arXiv:2112.05393(2021).Google Scholar
- Li Sun, Zhongbao Zhang, Jiawei Zhang, Feiyang Wang, Yang Du, Sen Su, and S Yu Philip. 2020. PERFECT: A Hyperbolic Embedding for Joint User and Community Alignment. In ICDM. IEEE, 501–510.Google Scholar
- Li Sun, Zhongbao Zhang, Jiawei Zhang, Feiyang Wang, Hao Peng, Sen Su, and Philip S Yu. 2021. Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs. In AAAI.Google Scholar
- Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Xingcheng Fu, Cheng Ji, and Philip S Yu. 2022. Graph Structure Learning with Variational Information Bottleneck. In AAAI.Google Scholar
- Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Yuanxing Ning, Philip S Yu, and Lifang He. 2021. Sugar: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In Web Conference. 2081–2091.Google ScholarDigital Library
- Qingyun Sun, Hao Peng, Jianxin Li, Senzhang Wang, Xiangyu Dong, Liangxuan Zhao, S Yu Philip, and Lifang He. 2020. Pairwise learning for name disambiguation in large-scale heterogeneous academic networks. In ICDM. IEEE, 511–520.Google Scholar
- Alexandru Tifrea, Gary Bécigneul, and Octavian-Eugen Ganea. 2019. Poincare Glove: Hyperbolic Word Embeddings. In ICLR.Google Scholar
- Abraham A Ungar. 1999. The hyperbolic Pythagorean theorem in the Poincaré disc model of hyperbolic geometry. The American mathematical monthly 106, 8 (1999), 759–763.Google Scholar
- Abraham A Ungar. 2005. Analytic hyperbolic geometry: Mathematical foundations and applications. World Scientific.Google Scholar
- Abraham Albert Ungar. 2008. A gyrovector space approach to hyperbolic geometry. Synthesis Lectures on Mathematics and Statistics 1, 1 (2008), 1–194.Google ScholarCross Ref
- Abraham Albert Ungar. 2014. Analytic hyperbolic geometry in n dimensions: An introduction. CRC Press.Google Scholar
- Petar Velickovic, William Fedus, William L. Hamilton, Pietro Lio’, Yoshua Bengio, and R. Devon Hjelm. 2019. Deep Graph Infomax. In ICLR.Google Scholar
- 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. 2508–2515.Google Scholar
- Shen Wang, Xiaokai Wei, Cicero dos Santos, Zhiguo Wang, Ramesh Nallapati, Andrew Arnold, Bing Xiang, and Philip S. Yu. 2020. H2KGAT: Hierarchical Hyperbolic Knowledge Graph Attention Network. In EMNLP. 4952–4962.Google Scholar
- Duncan J Watts and Steven H Strogatz. 1998. Collective dynamics of ‘small-world’networks. Nature 393, 6684 (1998), 440–442.Google Scholar
- Thomas James Willmore. 2013. An introduction to differential geometry. Courier Corporation.Google Scholar
- Richard C Wilson, Edwin R Hancock, Elżbieta Pekalska, and Robert PW Duin. 2014. Spherical and hyperbolic embeddings of data. IEEE transactions on pattern analysis and machine intelligence 36, 11(2014), 2255–2269.Google ScholarCross Ref
- Jia Wu, Xingquan Zhu, Chengqi Zhang, and Zhihua Cai. 2013. Multi-instance Multi-graph Dual Embedding Learning. In ICDM. 827–836.Google Scholar
- Jiacheng Xu and Greg Durrett. 2018. Spherical latent spaces for stable variational autoencoders. EMNLP (2018).Google Scholar
- Ze Ye, Kin Sum Liu, Tengfei Ma, Jie Gao, and Chao Chen. 2019. Curvature graph network. In ICLR.Google Scholar
- Wenchao Yu, Cheng Zheng, Wei Cheng, Charu C Aggarwal, Dongjin Song, Bo Zong, Haifeng Chen, and Wei Wang. 2018. Learning deep network representations with adversarially regularized autoencoders. In SIGKDD. 2663–2671.Google Scholar
- Shijie Zhu, Jianxin Li, Hao Peng, Senzhang Wang, and Lifang He. 2021. Adversarial Directed Graph Embedding. In AAAI, Vol. 35. 4741–4748.Google Scholar
- Arkaitz Zubiaga, Ahmet Aker, Kalina Bontcheva, Maria Liakata, and Rob Procter. 2018. Detection and resolution of rumours in social media: A survey. ACM Computing Surveys (CSUR) 51, 2 (2018), 1–36.Google ScholarDigital Library
Index Terms
- Curvature Graph Generative Adversarial Networks
Recommendations
Adaptive curvature exploration geometric graph neural network
AbstractGraph Neural networks (GNNs) which are powerful and widely applied models are based on the assumption that graph topologies play key roles in the graph representation learning.However, the existing GNN methods are based on the Euclidean space ...
Non-Euclidean Spring Embedders
We present a conceptually simple approach to generalizing force-directed methods for graph layout from Euclidean geometry to Riemannian geometries. Unlike previous work on non-Euclidean force-directed methods, ours is not limited to special classes of ...
Non-Euclidean Spring Embedders
INFOVIS '04: Proceedings of the IEEE Symposium on Information VisualizationWe present a method by which force-directed algorithms for graph layouts can be generalized to calculate the layout of a graph in an arbitrary Riemannian geometry. The method relies on extending the Euclidean notions of distance, angle, and force-...
Comments