Ming-Han Feng
ABSTRACT
Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.
- Amr Ahmed, Nino Shervashidze, Shravan Narayanamurthy, Vanja Josifovski, and Alexander J. Smola. {n. d.}. Distributed Large-scale Natural Graph Factorization(WWW '13). Google Scholar
Digital Library
- Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. {n. d.}. Freebase: a collaboratively created graph database for structuring human knowledge(SIGMOD '08). Google ScholarDigital Library
- Antoine Bordes, Xavier Glorot, Jason Weston, and Yoshua Bengio. 2014. A Semantic Matching Energy Function for Learning with Multi-relational Data. Machine Learning. Google ScholarDigital Library
- Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. {n. d.}. Translating embeddings for modeling multi-relational data(NIPS '13). Google ScholarDigital Library
- Antoine Bordes, Jason Weston, Ronan Collobert, and Yoshua Bengio. {n. d.}. Learning Structured Embeddings of Knowledge Bases(AAAI'11). Google ScholarDigital Library
- Bobby-Joe Breitkreutz, Chris Stark, Teresa Reguly, Lorrie Boucher, Ashton Breitkreutz, Michael Livstone, Rose Oughtred, Daniel H. Lackner, Jürg Bähler, Valerie Wood, Kara Dolinski, and Mike Tyers. 2008. The BioGRID Interaction Database: 2008 update. Nucleic Acids Research(2008), D637-D640.Google Scholar
- Shaosheng Cao, Wei Lu, and Qiongkai Xu. {n. d.}. Deep Neural Networks for Learning Graph Representations(AAAI'16). Google ScholarDigital Library
- Shaosheng Cao, Wei Lu, and Qiongkai Xu. {n. d.}. GraRep: Learning Graph Representations with Global Structural Information(CIKM '15). Google ScholarDigital Library
- Miao Fan, Qiang Zhou, Emily Chang, and Thomas Fang Zheng. {n. d.}. Transition-based Knowledge Graph Embedding with Relational Mapping Properties(PACLIC '14).Google Scholar
- Aditya Grover and Jure Leskovec. {n. d.}. node2vec: Scalable feature learning for networks(KDD '16). Google ScholarDigital Library
- Shizhu He, Kang Liu, Guoliang Ji, and Jun Zhao. {n. d.}. Learning to Represent Knowledge Graphs with Gaussian Embedding(CIKM '15). Google ScholarDigital Library
- Xiao Huang, Jundong Li, and Xia Hu. {n. d.}. Label Informed Attributed Network Embedding(WSDM '17). Google ScholarDigital Library
- Rodolphe Jenatton, Nicolas Le Roux, Antoine Bordes, and Guillaume Obozinski. {n. d.}. A Latent Factor Model for Highly Multi-relational Data(NIPS '12). Google ScholarDigital Library
- Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, and Jun Zhao. {n. d.}. Knowledge Graph Embedding via Dynamic Mapping Matrix.(ACL '15).Google Scholar
- Guoliang Ji, Kang Liu, Shizhu He, and Jun Zhao. {n. d.}. Knowledge Graph Completion with Adaptive Sparse Transfer Matrix(AAAI'16). Google ScholarDigital Library
- Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv (2014).Google Scholar
- Thomas N. Kipf and Max Welling. {n. d.}. Semi-Supervised Classification with Graph Convolutional Networks(ICLR '17).Google Scholar
- Denis Krompaβ, Stephan Baier, and Volker Tresp. {n. d.}. Type-Constrained Representation Learning in Knowledge Graphs(ISWC'15). Google ScholarDigital Library
- Yankai Lin, Zhiyuan Liu, and Maosong Sun. {n. d.}. Knowledge Representation Learning with Entities, Attributes and Relations(IJCAI'16). Google ScholarDigital Library
- Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. {n. d.}. Learning Entity and Relation Embeddings for Knowledge Graph Completion(AAAI'15). Google ScholarDigital Library
- Laurens van der Maaten and Geoffrey Hinton. {n. d.}. Visualizing data using t-SNE(JMLR '08).Google Scholar
- Matt Mahoney. 2011. Large Text Compression Benchmark. http://www.mattmahoney.net/dc/textdataGoogle Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. {n. d.}. Distributed Representations of Words and Phrases and their Compositionality(NIPS '13). Google ScholarDigital Library
- George A Miller. 1995. WordNet: a lexical database for English. Commun. ACM (1995). Google ScholarDigital Library
- Dat Quoc Nguyen. 2017. An overview of embedding models of entities and relationships for knowledge base completion. ArXiv (2017).Google Scholar
- Dat Quoc Nguyen, Kairit Sirts, Lizhen Qu, and Mark Johnson. {n. d.}. STransE: a novel embedding model of entities and relationships in knowledge bases(NAACL '16).Google Scholar
- Maximilian Nickel, Lorenzo Rosasco, and Tomaso Poggio. {n. d.}. Holographic Embeddings of Knowledge Graphs(AAAI'16). Google ScholarDigital Library
- Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. {n. d.}. A Three-way Model for Collective Learning on Multi-relational Data(ICML'11). Google ScholarDigital Library
- Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, and Wenwu Zhu. {n. d.}. Asymmetric Transitivity Preserving Graph Embedding(KDD '16). Google ScholarDigital Library
- Shirui Pan, Jia Wu, Xingquan Zhu, Chengqi Zhang, and Yang Wang. {n. d.}. Tri-party Deep Network Representation(IJCAI'16). Google ScholarDigital Library
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. {n. d.}. Deepwalk: Online learning of social representations(KDD '14). Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. {n. d.}. BPR: Bayesian personalized ranking from implicit feedback(UAI '09). Google ScholarDigital Library
- Leonardo F.R. Ribeiro, Pedro H.P. Saverese, and Daniel R. Figueiredo. {n. d.}. Struc2Vec: Learning Node Representations from Structural Identity(KDD '17). Google ScholarDigital Library
- Baoxu Shi and Tim Weninger. {n. d.}. ProjE: Embedding Projection for Knowledge Graph Completion(AAAI '17). Google ScholarDigital Library
- Richard Socher, Danqi Chen, Christopher D Manning, and Andrew Ng. {n. d.}. Reasoning With Neural Tensor Networks for Knowledge Base Completion. Google ScholarDigital Library
- Han Hee Song, Tae Won Cho, Vacha Dave, Yin Zhang, and Lili Qiu. {n. d.}. Scalable Proximity Estimation and Link Prediction in Online Social Networks(IMC '09).Google Scholar
- Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. {n. d.}. Line: Large-scale information network embedding(WWW '15). Google ScholarDigital Library
- Lei Tang and Huan Liu. {n. d.}. Relational Learning via Latent Social Dimensions(KDD '09). Google ScholarDigital Library
- Yi Tay, Anh Tuan Luu, Siu Cheung Hui, and Falk Brauer. {n. d.}. Random Semantic Tensor Ensemble for Scalable Knowledge Graph Link Prediction(WSDM '17). Google ScholarDigital Library
- Cunchao Tu, Weicheng Zhang, Zhiyuan Liu, and Maosong Sun. {n. d.}. Max-margin Deepwalk: Discriminative Learning of Network Representation(IJCAI'16). Google ScholarDigital Library
- Daixin Wang, Peng Cui, and Wenwu Zhu. {n. d.}. Structural deep network embedding(KDD '16). Google ScholarDigital Library
- Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, and Shiqiang Yang. {n. d.}. Community Preserving Network Embedding(AAAI'17). Google ScholarDigital Library
- Yujing Wang, Yunhai Tong, and Ming Zeng. 2013. Ranking Scientific Articles by Exploiting Citations, Authors, Journals, and Time Information. Google ScholarDigital Library
- Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. {n. d.}. Knowledge Graph Embedding by Translating on Hyperplanes(AAAI '14). Google ScholarDigital Library
- Xiaokai Wei, Linchuan Xu, Bokai Cao, and Philip S. Yu. {n. d.}. Cross View Link Prediction by Learning Noise-resilient Representation Consensus(WWW '17). Google ScholarDigital Library
- Gio Wiederhold. 1999. Movies. https://kdd.ics.uci.edu/databases/movies/movies.htmlGoogle Scholar
- Han Xiao, Minlie Huang, and Xiaoyan Zhu. {n. d.}. TransG : A Generative Model for Knowledge Graph Embedding(ACL '16).Google Scholar
- Ruobing Xie, Zhiyuan Liu, and Maosong Sun. {n. d.}. Representation Learning of Knowledge Graphs with Hierarchical Types(IJCAI'16). Google ScholarDigital Library
- Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. {n. d.}. Embedding Entities and Relations for Learning and Inference in Knowledge Bases(ICLR '15).Google Scholar
- Cheng Yang, Zhiyuan Liu, Deli Zhao, Maosong Sun, and Edward Y. Chang. {n. d.}. Network Representation Learning with Rich Text Information(IJCAI'15). Google ScholarDigital Library
- D. Zhang, J. Yin, X. Zhu, and C. Zhang. {n. d.}. Homophily, Structure, and Content Augmented Network Representation Learning(ICDM'16).Google Scholar
- Chang Zhou, Yuqiong Liu, Xiaofei Liu, Zhongyi Liu, and Jun Gao. {n. d.}. Scalable Graph Embedding for Asymmetric Proximity(AAAI'17). Google ScholarDigital Library
Recommendations
Mixed-Curvature Multi-Relational Graph Neural Network for Knowledge Graph Completion
WWW '21: Proceedings of the Web Conference 2021Knowledge graphs (KGs) have gradually become valuable assets for many AI applications. In a KG, a node denotes an entity, and an edge (or link) denotes a relationship between the entities represented by the nodes. Knowledge graph completion infers and ...
A vectorized relational graph convolutional network for multi-relational network alignment
IJCAI'19: Proceedings of the 28th International Joint Conference on Artificial IntelligenceAlignment of multiple multi-relational networks, such as knowledge graphs, is vital for AI applications. Different from the conventional alignment models, we apply the graph convolutional network (GCN) to achieve more robust network embedding for the ...
A survey on reversible watermarking techniques for relational databases
Over the past few years, reversible watermarking techniques for relational databases have been proposed to provide protection of ownership rights, data tempering, and data integrity. Mainly, these techniques ensure original data recovery from ...
Comments