ABSTRACT
Network embedding learns the vector representations of nodes. Most real world networks are heterogeneous and evolve over time. There are, however, no network embedding approaches designed for dynamic heterogeneous networks so far. Addressing this research gap is beneficial for analyzing and mining real world networks. We develop a novel representation learning method, change2vec, which considers a dynamic heterogeneous network as snapshots of networks with different time stamps. Instead of processing the whole network at each time stamp, change2vec models changes between two consecutive static networks by capturing newly-added and deleted nodes with their neighbour nodes as well as newly-formed or deleted edges that caused core structural changes known as triad closure or open processes. Change2vec leverages metapath based node embedding and change modeling to preserve both heterogeneous and dynamic features of a network. Experimental results show that change2vec outperforms two state-of-the-art methods in terms of clustering performance and efficiency.
- Shiyu Chang, Wei Han, Jiliang Tang, Guo-Jun Qi, Charu C. Aggarwal, and Thomas S. Huang. 2015. Heterogeneous network embedding via deep architectures. In Proceedings of the 21st ACM SIGKDD. 119--128. Google ScholarDigital Library
- Yuxiao Dong, Nitesh V. Chawla, and Ananthram Swami. 2017. Metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD. 135--144. Google ScholarDigital Library
- Aditya Grover and Jure Leskovec. 2016. Node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD. 855--864. Google ScholarDigital Library
- Hong Huang, Jie Tang, Lu Liu, Jar Der Luo, and Xiaoming Fu. 2015. Triadic closure pattern analysis and prediction in social networks. IEEE Transactions on Knowledge and Data Engineering27, 12 (2015), 3374--3389. Google ScholarDigital Library
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems26 (2013), 3111--3119. Google ScholarDigital Library
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deep Walk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD. 701--710. Google ScholarDigital Library
- Yizhou Sun, Jiawei Han, Peixiang Zhao, Zhijun Yin, Hong Cheng, and Tianyi Wu. 2009. Rank Clus: Integrating clustering with ranking for heterogeneous information network analysis. In Proceedings of the 12th EDBT. 565--576. Google ScholarDigital Library
- Silke Wagner and Dorothea Wagner. 2007. Comparing clusterings: an overview.Google Scholar
- Duncan J Watts and Steven H Strogatz. 1998. Collective dynamics of 'small-world' networks. Nature 393, 6684 (1998), 440.Google Scholar
- Lekui Zhou, Yang Yang, Xiang Ren, Fei Wu, and Yueting Zhuang. 2018. Dynamic network embedding by modeling triadic closure process. In Proceedings of the 32nd AAAI.Google Scholar
- Linhong Zhu, Dong Guo, Junming Yin, Greg Ver Steeg, and Aram Galstyan. 2016. Scalable temporal latent space inference for link prediction in dynamic social networks. IEEE Transactions on Knowledge and Data Engineering 28, 10 (2016),2765 -- 2777. Google ScholarDigital Library
Recommendations
Adaptive Optimization of Dynamic Heterogeneous Network Topologies: A Simulated Annealing Methodology
Artificial Intelligence and SecurityAbstractThe subnetwork architecture and dynamic optimization difficulties of a dynamic heterogeneous network must be investigated in order to handle the rising number of nodes and links. For the difficult challenge of dynamic network topology changing in ...
Multi-view Heterogeneous Network Embedding
Knowledge Science, Engineering and ManagementAbstractIn the real world, the complex and diverse relations among different objects can be described in the form of networks. At the same time, with the emergence and development of network embedding, it has become an effective tool for processing ...
Dynamic Heterogeneous Graph Embedding Using Hierarchical Attentions
Advances in Information RetrievalAbstractGraph embedding has attracted many research interests. Existing works mainly focus on static homogeneous/heterogeneous networks or dynamic homogeneous networks. However, dynamic heterogeneous networks are more ubiquitous in reality, e.g. social ...
Comments