DINE: A Framework for Deep Incomplete Network Embedding

Abstract

Network representation learning (NRL) plays a vital role in a variety of tasks such as node classification and link prediction. It aims to learn low-dimensional vector representations for nodes based on network structures or node attributes. While embedding techniques on complete networks have been intensively studied, in real-world applications, it is still a challenging task to collect complete networks. To bridge the gap, in this paper, we propose a Deep Incomplete Network Embedding method, namely DINE. Specifically, we first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework. To improve the embedding performance, we consider both network structures and node attributes to learn node representations. Empirically, we evaluate DINE over three networks on multi-label classification and link prediction tasks. The results demonstrate the superiority of our proposed approach compared against state-of-the-art baselines.

12 pages, 3 figures

References in corpus (7)

• LINE: Large-scale Information Network Embedding
• Hierarchical structure and the prediction of missing links in networks
• Missing and spurious interactions and the reconstruction of complex networks
• Kronecker Graphs: An Approach to Modeling Networks
• PIS: A Multi-dimensional Routing Protocol for Socially-aware Networking
• Socially-Aware Conference Participant Recommendation with Personality Traits
• Judging a Book by Its Cover: The Effect of Facial Perception on Centrality in Social Networks