Discrete Network Embedding

Network embedding aims to seek low-dimensional vector representations for network nodes, by preserving the network structure. The network embedding is typically represented in continuous vector, which imposes formidable challenges in storage and computation costs, particularly in large-scale applications. To address the issue, this paper proposes a novel discrete network embedding (DNE) for more compact representations. In particular, DNE learns short binary codes to represent each node. The Hamming similarity between two binary embeddings is then employed to well approximate the ground-truth similarity. A novel discrete multi-class classifier is also developed to expedite classification. Moreover, we propose to jointly learn the discrete embedding and classifier within a unified framework to improve the compactness and discrimination of network embedding. Extensive experiments on node classification consistently demonstrate that DNE exhibits lower storage and computational complexity than state-of-the-art network embedding methods, while obtains competitive classification results.

Authors

• Xiaobo Shen Nanjing University of Science and Technology
• Shirui Pan Griffith University, Queensland, Australia
• Weiwei Liu Wuhan University
• Yew-Soon Ong Centre for Frontier AI Research, A*STAR & College of Computing and Data Science, NTU
• Quan-Sen Sun

Keywords

• Machine Learning Applications: Networks
• Machine Learning: Data Mining
• Machine Learning: Relational Learning