Graph Learning:… (2021-04-01T00:00:00.000000Z)

TL;DR

A comprehensive overview on the state of the art of graph learning is presented, including graph signal processing, matrix factorization, random walk, and deep learning, and major models and algorithms under these categories are reviewed respectively.

Abstract

Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field.

Authors

Huan Liu

7 papers

Feng Xia

1 papers

Ke Sun

6 papers

References190 items

A3Graph: adversarial attributed autoencoder for graph representation learning

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Graph Force Learning

Network embedding: Taxonomies, frameworks and applications

OFFER: A Motif Dimensional Framework for Network Representation Learning

Abstract

References190 items

TL;DR

Abstract

Authors

References190 items

A3Graph: adversarial attributed autoencoder for graph representation learning

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Graph Force Learning

Network embedding: Taxonomies, frameworks and applications

OFFER: A Motif Dimensional Framework for Network Representation Learning

TL;DR

Abstract

Authors

References190 items

A3Graph: adversarial attributed autoencoder for graph representation learning

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Graph Force Learning

Network embedding: Taxonomies, frameworks and applications

OFFER: A Motif Dimensional Framework for Network Representation Learning

Data-driven Computational Social Science: A Survey

Multivariate Relations Aggregation Learning in Social Networks

Big Networks: A Survey

Web of Scholars: A Scholar Knowledge Graph

Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning

Ranking Station Importance With Human Mobility Patterns Using Subway Network Datasets

Reinforcement Learning Based Meta-Path Discovery in Large-Scale Heterogeneous Information Networks

GSSNN: Graph Smoothing Splines Neural Networks

Random Walks: A Review of Algorithms and Applications

A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

Graduate Employment Prediction with Bias

Shifu2: A Network Representation Learning Based Model for Advisor-Advisee Relationship Mining

To Your Surprise: Identifying Serendipitous Collaborators

Graph WaveNet for Deep Spatial-Temporal Graph Modeling

BASES.

Sustainable Collaborator Recommendation Based on Conference Closure

Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey

SHNE: Representation Learning for Semantic-Associated Heterogeneous Networks

Learning Graph Embedding With Adversarial Training Methods

Deep Learning on Graphs: A Survey

Are Meta-Paths Necessary?: Revisiting Heterogeneous Graph Embeddings

Rating Prediction via Graph Signal Processing

Graph Convolutional Networks for Text Classification

Graph Classification using Structural Attention

Large-Scale Learnable Graph Convolutional Networks

Deep Recursive Network Embedding with Regular Equivalence

Embedding Temporal Network via Neighborhood Formation

Learning Steady-States of Iterative Algorithms over Graphs

Machine learning for molecular and materials science

Deep Reasoning with Knowledge Graph for Social Relationship Understanding

Graph-to-Sequence Learning using Gated Graph Neural Networks

REVISED NOTE ON LEARNING QUADRATIC ASSIGNMENT WITH GRAPH NEURAL NETWORKS

Sentence-State LSTM for Text Representation

Continuous-Time Dynamic Network Embeddings

Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification

Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN

Artificial Intelligence in the 21st Century

GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs

A Graph Signal Processing Perspective on Functional Brain Imaging

NetGAN: Generating Graphs via Random Walks

Science of Science

Learning Deep Generative Models of Graphs

Analysis of Online Social Network Connections for Identification of Influential Users

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Network Representation Learning: A Survey

Graph Signal Processing: Overview, Challenges, and Applications

Knowledge Graph Embedding: A Survey of Approaches and Applications

Heterogeneous Information Network Embedding for Recommendation

GraphGAN: Graph Representation Learning with Generative Adversarial Nets

Multi-label Zero-Shot Learning with Structured Knowledge Graphs

Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classification

HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning

Learning to Represent Programs with Graphs

Distributed Representations of Subgraphs

Graph Attention Networks

Watch Your Step: Learning Node Embeddings via Graph Attention

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

graph2vec: Learning Distributed Representations of Graphs

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly