3-in-1 Correlated Embedding via Adaptive Exploration of the Structure and Semantic Subspaces

3-in-1 Correlated Embedding via Adaptive Exploration of the Structure and Semantic Subspaces

Liang Yang, Yuanfang Guo, Di Jin, Huazhu Fu, Xiaochun Cao

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 3613-3619. https://doi.org/10.24963/ijcai.2018/502

Combinational  network embedding, which learns the node representation by exploring both  topological and non-topological information, becomes popular due to the fact that the two types of information are complementing each other.  Most of the existing methods either consider the  topological and non-topological  information being aligned or possess predetermined preferences during the embedding process.Unfortunately, previous methods  fail to either explicitly describe the correlations between topological and non-topological information or adaptively weight their impacts. To address the existing issues, three new assumptions are proposed to better describe the embedding space and its properties. With the proposed assumptions, nodes, communities and topics are mapped into one embedding space. A novel generative model is proposed to formulate the generation process of the network and content from the embeddings, with respect to the Bayesian framework. The proposed model automatically leans to the information which is more discriminative.The embedding result can be obtained by maximizing the posterior distribution by adopting the variational inference and reparameterization trick. Experimental results indicate that the proposed method gives superior performances compared to the state-of-the-art methods when a variety of real-world networks is analyzed.
Keywords:
Machine Learning Applications: Networks
Multidisciplinary Topics and Applications: AI and the Web