Graph Learning: A Survey

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.

arXiv comment19 pages, 6 figures

References in corpus (33)

• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Graph Embedding Techniques, Applications, and Performance: A Survey
• A Review of Relational Machine Learning for Knowledge Graphs
• Discrete Signal Processing on Graphs
• Learning Combinatorial Optimization Algorithms over Graphs
• PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• Discrete Signal Processing on Graphs: Sampling Theory
• Large-Scale Learnable Graph Convolutional Networks
• Dynamic Graph Convolutional Networks
• Learning Graph Embedding with Adversarial Training Methods
• Sampling of graph signals with successive local aggregations
• Random Walks: A Review of Algorithms and Applications
• Kernel-based Reconstruction of Graph Signals
• Signal Processing on Graphs: Causal Modeling of Unstructured Data
• Local-set-based Graph Signal Reconstruction
• Greedy Sampling of Graph Signals
• Watch Your Step: Learning Node Embeddings via Graph Attention
• Adaptive Least Mean Squares Estimation of Graph Signals
• Scientific Article Recommendation: Exploiting Common Author Relations and Historical Preferences
• Reconstruction of Graph Signals through Percolation from Seeding Nodes
• Blind Identification of Graph Filters
• Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
• Data-driven Computational Social Science: A Survey
• A Distributed Tracking Algorithm for Reconstruction of Graph Signals
• Discrete Signal Reconstruction by Sum of Absolute Values
• The Spacey Random Walk: a Stochastic Process for Higher-order Data
• Big Networks: A Survey
• Learning Graphs with Monotone Topology Properties and Multiple Connected Components
• Multivariate Relations Aggregation Learning in Social Networks
• Turing Number: How Far Are You to A. M. Turing Award?

Cited by in corpus (33)

• A Review of Generalized Zero-Shot Learning Methods
• A Comprehensive Survey on Deep Graph Representation Learning
• Graph-based Deep Learning for Communication Networks: A Survey
• Anomaly Detection in Dynamic Graphs via Transformer
• Attention-based graph neural networks: a survey
• Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection
• Exploring Human Mobility for Multi-Pattern Passenger Prediction: A Graph Learning Framework
• Moving Object Detection for Event-based vision using Graph Spectral Clustering
• CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs
• Multiple Instance Learning for Cheating Detection and Localization in Online Examinations
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
• Privacy-Preserving Individual-Level COVID-19 Infection Prediction via Federated Graph Learning
• Deep Outdated Fact Detection in Knowledge Graphs
• Sparse Graph Learning Under Laplacian-Related Constraints
• Joint Network Topology Inference in the Presence of Hidden Nodes
• Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines
• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network
• Graph Representation Learning for Popularity Prediction Problem: A Survey
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Entropy Causal Graphs for Multivariate Time Series Anomaly Detection
• Digital Twin Mobility Profiling: A Spatio-Temporal Graph Learning Approach
• Continual Graph Learning: A Survey
• Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
• Refined Causal Graph Structure Learning via Curvature for Brain Disease Classification
• Quality-diversity in dissimilarity spaces
• Riemannian Graph Tokenizer for Structural Knowledge Transfer
• Bi-View Embedding Fusion: A Hybrid Learning Approach for Knowledge Graph's Nodes Classification Addressing Problems with Limited Data
• Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning
• Mapping bipartite networks into multidimensional hyperbolic spaces
• Hierarchical graph sampling based minibatch learning with chain preservation and variance reduction
• A Structural Feature-Based Approach for Comprehensive Graph Classification
• Lightweight Cryptanalysis of IoT Encryption Algorithms : Is Quota Sampling the Answer?