Learning distributed representations from network data and human navigation

2017-12-13The increasing growth of network data such as online social networks and linked documents on the Web, has imposed great challenges on automatic feature generation for data analysis. We study the problem of learning representations from network data, which is of critical for real applications including document search, personalized recommendation and role discovery. Most existing approaches do not characterize the surrounding network structure that serves as the context of each data point, or are not scalable to large-scale data in real world scenarios. ❧ We present novel neural network algorithms to learn distributed representations of network data by exploiting network structures and human navigation trails. The algorithms embed data points into a common low-dimensional continuous vector space, which facilitates predictive tasks such as classification, relational learning and analogy. To improve the scalability, we adopt efficient optimization and sampling methods in our algorithms. ❧ Firstly, we propose a neural embedding algorithm to learn distributed representations of generic graphs with global context. In order to represent the global network structure, a global vector is used to learn the structural information collectively from all local neighborhoods of nodes in a network. Our algorithm is scalable and the learned global representations can be used for similarity measurement between two networks. We evaluate our algorithm against the state-of-the-art methods, and present empirical results on node classification, role discovery and analogy tasks. ❧ Secondly, we present a neural language model to learn text representations from networked documents. This is based on the intuition that authors are influenced by words in the documents they cite and readers usually comprehend the words in paragraphs by referring to those cited concepts or documents. The model can capture both the local context of word sequences and the semantic influence between linked documents. We show improved performance on document classification and link prediction tasks with our model. ❧ Thirdly, the information of how users navigate the network data online provide clues about missing links between cognitively similar concepts. Learning from human navigation trails online can also help characterizing human behavior and improving recommendation. We devise another neural network algorithm to model human navigation of text documents in a hierarchical manner. The model can learn representations of text documents by accounting for human navigation patterns, and hence is better linked to human cognition. We present empirical results of our algorithm on real news and movie review datasets, and show its effectiveness on document classification, search and recommendation tasks