ABSTRACT
Representation learning on graphs, also called graph embedding, has demonstrated its significant impact on a series of machine learning applications such as classification, prediction and recommendation. However, existing work has largely ignored the rich information contained in the properties (or attributes) of both nodes and edges of graphs in modern applications, e.g., those represented by property graphs. To date, most existing graph embedding methods either focus on plain graphs with only the graph topology, or consider properties on nodes only. We propose PGE, a graph representation learning framework that incorporates both node and edge properties into the graph embedding procedure. PGE uses node clustering to assign biases to differentiate neighbors of a node and leverages multiple data-driven matrices to aggregate the property information of neighbors sampled based on a biased strategy. PGE adopts the popular inductive model for neighborhood aggregation. We provide detailed analyses on the efficacy of our method and validate the performance of PGE by showing how PGE achieves better embedding results than the state-of-the-art graph embedding methods on benchmark applications such as node classification and link prediction over real-world datasets.
- Nitin Agarwal, Huan Liu, Sudheendra Murthy, Arunabha Sen, and Xufei Wang. A social identity approach to identify familiar strangers in a social network. In ICWSM, 2009.Google Scholar
- Amr Ahmed, Nino Shervashidze, Shravan M. Narayanamurthy, Vanja Josifovski, and Alexander J. Smola. Distributed large-scale natural graph factorization. In WWW, pages 37--48, 2013. Google ScholarDigital Library
- Eytan Bakshy, Itamar Rosenn, Cameron Marlow, and Lada A. Adamic. The role of social networks in information diffusion. In WWW, pages 519--528, 2012. Google ScholarDigital Library
- Mauro Barone and Michele Coscia. Birds of A feather scam together: Trustworthiness homophily in A business network. Social Networks, 54.Google Scholar
- Yoshua Bengio, Aaron C. Courville, and Pascal Vincent. Representation learning: A review and new perspectives. PAMI, 35:1798--1828, 2013. Google ScholarDigital Library
- Smriti Bhagat, Graham Cormode, and S. Muthukrishnan. Node classification in social networks. In Social network datanalytics, pages 115--148. 2011.Google ScholarCross Ref
- Michael M. Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. Geometric deep learning: Going beyond euclidean data. IEEE Signal Processing Magazine, 34.Google Scholar
- Shaosheng Cao, Wei Lu, and Qiongkai Xu. Grarep: Learning graph representations with global structural information. In CIKM, pages 891--900, 2015. Google ScholarDigital Library
- Shaosheng Cao, Wei Lu, and Qiongkai Xu. Deep neural networks for learning graph representations. In AAAI, pages 1145--1152, 2016. Google ScholarDigital Library
- Haochen Chen, Bryan Perozzi, Yifan Hu, and Steven Skiena. HARP: hierarchical representation learning for networks. In AAAI, pages 2127--2134, 2018.Google Scholar
- Jianfei Chen, Jun Zhu, and Le Song. Stochastic training of graph convolutional networks with variance reduction. In ICML, pages 941--949, 2018.Google Scholar
- Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu. A density-based algorithm for discovering clusters in large spatial databases with noise. In SIGKDD, pages 226--231, 1996. Google ScholarDigital Library
- Santo Fortunato. Community detection in graphs. Physics Reports, 486:75--174, 2010.Google ScholarCross Ref
- Thomas Gärtner, Tamás Horváth, and Stefan Wrobel. Graph kernels. In Encyclopedia of Machine Learning and Data Mining, pages 579--581. 2017.Google ScholarCross Ref
- Palash Goyal and Emilio Ferrara. Graph embedding techniques, applications, and performance: A survey. KBS, 151:78--94, 2018.Google ScholarCross Ref
- Aditya Grover and Jure Leskovec. node2vec: Scalable feature learning for networks. In SIGKDD, pages 855--864, 2016. Google ScholarDigital Library
- William L. Hamilton, Rex Ying, and Jure Leskovec. Representation learning on graphs: Methods and applications. IEEE Data Eng. Bull., 40:52--74, 2017.Google Scholar
- William L. Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NIPS, pages 1024--1034, 2017. Google ScholarDigital Library
- Keith Henderson, Brian Gallagher, Tina Eliassi-Rad, Hanghang Tong, Sugato Basu, Leman Akoglu, Danai Koutra, Christos Faloutsos, and Lei Li. Rolx: Structural role extraction & mining in large graphs. In SIGKDD, pages 1231--1239, 2012. Google ScholarDigital Library
- Geoffrey E. Hinton and Ruslan R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313:504--507, 2006.Google ScholarCross Ref
- Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.Google Scholar
- Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. CoRR, 2016.Google Scholar
- Thomas N. Kipf and Max Welling. Variational graph auto-encoders. CoRR, 2016.Google Scholar
- David Liben-Nowell and Jon M. Kleinberg. The link-prediction problem for social networks. JASIST, 58:1019--1031, 2007. Google ScholarDigital Library
- James MacQueen. Some methods for classification and analysis of multivariate observations. In Berkeley Symposium on Mathematical Statistics and Probability, volume 1, pages 281--297, 1967.Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. Distributed representations of words and phrases and their compositionality. In NIPS, pages 3111--3119, 2013. Google ScholarDigital Library
- Galileo Namata, Ben London, Lise Getoor, Bert Huang, and UMD EDU. Querydriven active surveying for collective classification. In MLG, 2012.Google Scholar
- Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 104.Google Scholar
- Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, and Wenwu Zhu. Asymmetric transitivity preserving graph embedding. In SIGKDD, pages 1105--1114, 2016. Google ScholarDigital Library
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social representations. In SIGKDD, pages 701--710, 2014. Google ScholarDigital Library
- Bryan Perozzi, Vivek Kulkarni, and Steven Skiena. Walklets: Multiscale graph embeddings for interpretable network classification. CoRR, 2016.Google Scholar
- Dragomir R. Radev, Hong Qi, HarrisWu, andWeiguo Fan. Evaluating web-based question answering systems. In LREC, 2002.Google Scholar
- Yutaka Sasaki. The truth of the f-measure. Teach Tutor Mater, 1:1--5, 2007.Google Scholar
- Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. Modeling relational data with graph convolutional networks. In ESWC, pages 593--607, 2018.Google Scholar
- Chris Stark, Bobby-Joe Breitkreutz, Teresa Reguly, Lorrie Boucher, Ashton Breitkreutz, and Mike Tyers. Biogrid: A general repository for interaction datasets. Nucleic Acids Research, 34:535--539, 2006.Google ScholarCross Ref
- Daixin Wang, Peng Cui, and Wenwu Zhu. Structural deep network embedding. In SIGKDD, pages 1225--1234, 2016. Google ScholarDigital Library
- Jaewon Yang and Jure Leskovec. Overlapping communities explain coreperiphery organization of networks. Proceedings of the IEEE, 102.Google Scholar
Index Terms
- A Representation Learning Framework for Property Graphs
Recommendations
Dual-decoder graph autoencoder for unsupervised graph representation learning
AbstractUnsupervised graph representation learning is a challenging task that embeds graph data into a low-dimensional space without label guidance. Recently, graph autoencoders have been proven to be an effective way to solve this problem in ...
Topological Graph Representation Learning on Property Graph
Knowledge Science, Engineering and ManagementAbstractProperty graph representation learning is using the property features from the graph to build the embeddings over the nodes and edges. There are many graph application tasks are using the property graph representation learning as part of the ...
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
WWW '19: The World Wide Web ConferenceCan neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e. feature engineering or labeled graphs). ...
Comments