Tutorial on NLP-Inspired Network Embedding
It provides an overview of online learning techniques for network embeddings, useful for analyzing graphs like social networks, but is incremental as it summarizes existing work.
This tutorial reviews recent methods for network embedding, which map graph nodes to vectors to preserve graph structure for tasks like link prediction, covering techniques such as DeepWalk, LINE, node2vec, struc2vec, and megapath2vec.
This tutorial covers a few recent papers in the field of network embedding. Network embedding is a collective term for techniques for mapping graph nodes to vectors of real numbers in a multidimensional space. To be useful, a good embedding should preserve the structure of the graph. The vectors can then be used as input to various network and graph analysis tasks, such as link prediction. The papers discussed develop methods for the online learning of such embeddings, and include DeepWalk, LINE, node2vec, struc2vec and megapath2vec. These new methods and developments in online learning of network embeddings have major applications for the analysis of graphs and networks, including online social networks.