Properties of Vector Embeddings in Social Networks
Open Access
- 27 September 2017
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 10 (4) , 109
Abstract
Embedding social network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification, node clustering, link prediction and network visualization. However, the information contained in these vector embeddings remains abstract and hard to interpret. Methods for inspecting embeddings usually rely on visualization methods, which do not work on a larger scale and do not give concrete interpretations of vector embeddings in terms of preserved network properties (e.g., centrality or betweenness measures). In this paper, we study and investigate network properties preserved by recent random walk-based embedding procedures like node2vec, DeepWalk or LINE. We propose a method that applies learning to rank in order to relate embeddings to network centralities. We evaluate our approach with extensive experiments on real-world and artificial social networks. Experiments show that each embedding method learns different network properties. In addition, we show that our graph embeddings in combination with neural networks provide a computationally efficient way to approximate the Closeness Centrality measure in social networks.Keywords
This publication has 36 references indexed in Scilit:
- Unifying Virtual and Physical WorldsACM Transactions on Information Systems, 2017
- BiRank: Towards Ranking on Bipartite GraphsIEEE Transactions on Knowledge and Data Engineering, 2016
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-imagesInternational Journal of Computer Vision, 2016
- Discovering social circles in ego networksACM Transactions on Knowledge Discovery From Data, 2014
- Visualization of Graph ProductsIEEE Transactions on Visualization and Computer Graphics, 2010
- Predicting the popularity of online contentCommunications of the ACM, 2010
- The link‐prediction problem for social networksJournal of the American Society for Information Science and Technology, 2007
- Empirical Analysis of an Evolving Social NetworkScience, 2006
- A measure of betweenness centrality based on random walksSocial Networks, 2005
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951