Network Representation Learning: A Survey

Abstract

With the widespread use of information technologies, information networks are becoming increasingly popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks, and biological networks. Analyzing these networks sheds light on different aspects of social life such as the structure of societies, information diffusion, and communication patterns. In reality, however, the large scale of information networks often makes network analytic tasks computationally expensive or intractable. Network representation learning has been recently proposed as a new learning paradigm to embed network vertices into a low-dimensional vector space, by preserving network topology structure, vertex content, and other side information. This facilitates the original network to be easily handled in the new vector space for further analysis. In this survey, we perform a comprehensive review of the current literature on network representation learning in the data mining and machine learning field. We propose new taxonomies to categorize and summarize the state-of-the-art network representation learning techniques according to the underlying learning mechanisms, the network information intended to preserve, as well as the algorithmic designs and methodologies. We summarize evaluation protocols used for validating network representation learning including published benchmark datasets, evaluation methods, and open source algorithms. We also perform empirical studies to compare the performance of representative algorithms on common datasets, and analyze their computational complexity. Finally, we suggest promising research directions to facilitate future study.

Accepted by IEEE transactions on Big Data; 25 pages, 10 tables, 6 figures and 127 references

References in corpus (14)

• Modularity and community structure in networks
• Improving neural networks by preventing co-adaptation of feature detectors
• Finding community structure in networks using the eigenvectors of matrices
• Inductive Representation Learning on Large Graphs
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Supervised Dictionary Learning
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Attributed Network Embedding for Learning in a Dynamic Environment
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• Heterogeneous Information Network Embedding for Meta Path based Proximity
• Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content
• Structural Deep Embedding for Hyper-Networks
• Adversarial Network Embedding
• An Attention-based Collaboration Framework for Multi-View Network Representation Learning

Cited by in corpus (10)

• Representation Learning for Natural Language Processing
• On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?
• FSCNMF: Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• Flexible Attributed Network Embedding
• MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding
• A Graph Convolutional Network Composition Framework for Semi-supervised Classification
• DINE: A Framework for Deep Incomplete Network Embedding