Representation Learning on Graphs: Methods and Applications

Abstract

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. Here we provide a conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. We review methods to embed individual nodes as well as approaches to embed entire (sub)graphs. In doing so, we develop a unified framework to describe these recent approaches, and we highlight a number of important applications and directions for future work.

Published in the IEEE Data Engineering Bulletin, September 2017; version with minor corrections

Cited by in corpus (54)

• Graph Contrastive Learning with Adaptive Augmentation
• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• Community Interaction and Conflict on the Web
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Operationalizing Individual Fairness with Pairwise Fair Representations
• SE-KGE: A Location-Aware Knowledge Graph Embedding Model for Geographic Question Answering and Spatial Semantic Lifting
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• Principled approach to the selection of the embedding dimension of networks
• Representation Learning over Dynamic Graphs
• MeshGAN: Non-linear 3D Morphable Models of Faces
• Graph Mining for Cybersecurity: A Survey
• Graph Neural Networks: Methods, Applications, and Opportunities
• Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation
• Implementing graph neural networks with TensorFlow-Keras
• Network representation learning systematic review: ancestors and current development state
• Socially Enhanced Situation Awareness from Microblogs using Artificial Intelligence: A Survey
• Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?
• A Framework for Quantifying Controversy of Social Network Debates Using Attributed Networks: Biased Random Walk (BRW)
• Using Embeddings to Correct for Unobserved Confounding in Networks
• Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach
• Pre-training Graph Neural Networks with Kernels
• Identification of Patterns in Cosmic-Ray Arrival Directions using Dynamic Graph Convolutional Neural Networks
• AliGraph: A Comprehensive Graph Neural Network Platform
• The Graph Database Interface: Scaling Online Transactional and Analytical Graph Workloads to Hundreds of Thousands of Cores
• Graph-Based Machine Learning Improves Just-in-Time Defect Prediction
• Marius: Learning Massive Graph Embeddings on a Single Machine
• LinkNBed: Multi-Graph Representation Learning with Entity Linkage
• Network Embedding via Deep Prediction Model
• Position-Aware Subgraph Neural Networks with Data-Efficient Learning
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• Quaternion Graph Neural Networks
• Representation Learning on Graphs: A Reinforcement Learning Application
• A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
• Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective
• Empirical effect of graph embeddings on fraud detection/ risk mitigation
• Learning Interpretable Disease Self-Representations for Drug Repositioning
• Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
• End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph
• Cultivating Online: Question Routing in a Question and Answering Community for Agriculture
• InteractionNet: Modeling and Explaining of Noncovalent Protein-Ligand Interactions with Noncovalent Graph Neural Network and Layer-Wise Relevance Propagation
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
• Normalized topological indices discriminate between architectures of branched macromolecules
• Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling
• User Donations in a Crowdsourced Video System
• Adversarial Model for Rotated Indoor Scenes Planning
• Deep Layout of Custom-size Furniture through Multiple-domain Learning
• Complex network prediction using deep learning
• Learning flexible representations of stochastic processes on graphs
• Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks