Network Representation Learning: From Traditional Feature Learning to Deep Learning

Abstract

Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field.

References in corpus (30)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Community detection in graphs
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Graph Embedding Techniques, Applications, and Performance: A Survey
• A Review of Relational Machine Learning for Knowledge Graphs
• word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
• Graph Convolutional Matrix Completion
• Adversarial Attacks on Neural Networks for Graph Data
• word2vec Parameter Learning Explained
• Predicting multicellular function through multi-layer tissue networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Spectral methods for network community detection and graph partitioning
• A Gentle Introduction to Deep Learning for Graphs
• Random Walks: A Review of Algorithms and Applications
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Adversarial Attacks on Node Embeddings via Graph Poisoning
• Hierarchical Graph Pooling with Structure Learning
• Fast Robust PCA on Graphs
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
• Signed Graph Convolutional Network
• Neural Embeddings of Graphs in Hyperbolic Space
• Detecting Overlapping Communities in Networks Using Spectral Methods
• The Weisfeiler-Lehman Method and Graph Isomorphism Testing
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Neural Graph Machines: Learning Neural Networks Using Graphs
• A Survey on Dynamic Network Embedding
• Heterogeneous Graph Attention Network