A Gentle Introduction to Deep Learning for Graphs

Abstract

The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs. It favours a consistent and progressive introduction of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view to the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. It introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. The methodological exposition is complemented by a discussion of interesting research challenges and applications in the field.

References in corpus (11)

• Semi-Supervised Classification with Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Variational Graph Auto-Encoders
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Self-Attention Graph Pooling
• Artificial Intelligence and Statistics
• A Fair Comparison of Graph Neural Networks for Graph Classification
• Edge-based sequential graph generation with recurrent neural networks
• Improved large-scale graph learning through ridge spectral sparsification
• Deep Tree Transductions - A Short Survey

Cited by in corpus (53)

• A Comprehensive Survey on Deep Graph Representation Learning
• An Overview of Deep Semi-Supervised Learning
• Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
• Benchmarking Graph Neural Networks
• BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
• Graph Neural Networks: Taxonomy, Advances and Trends
• Adaptive Propagation Graph Convolutional Network
• Deep Learning for Satellite Image Time Series Analysis: A Review
• FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning
• Power Flow Balancing with Decentralized Graph Neural Networks
• A Survey on Hyperlink Prediction
• Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces
• Graph Neural Networks for Graph Drawing
• Graph neural network-based fault diagnosis: a review
• Deep learning for dynamic graphs: models and benchmarks
• Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization
• Graph Neural Network for Stress Predictions in Stiffened Panels Under Uniform Loading
• Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• Graph Deep Learning for Time Series Forecasting
• Distributed Training of Graph Convolutional Networks
• Transition Propagation Graph Neural Networks for Temporal Networks
• Explaining Deep Graph Networks with Molecular Counterfactuals
• Addressing Heterophily in Node Classification with Graph Echo State Networks
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• Predictive Auto-scaling with OpenStack Monasca
• Model-based inexact graph matching on top of CNNs for semantic scene understanding
• Dynamic Graph Echo State Networks
• Some open questions on morphological operators and representations in the deep learning era
• Tensor Decompositions in Deep Learning
• Low Complexity Approaches for End-to-End Latency Prediction
• Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
• Generalizing Downsampling from Regular Data to Graphs
• Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
• Self-Tuning Hamiltonian Monte Carlo for Accelerated Sampling
• Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
• Graph Mixture Density Networks
• Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation
• Beyond Homophily with Graph Echo State Networks
• Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations
• Modeling Edge Features with Deep Bayesian Graph Networks
• Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
• Efficient quantification on large-scale networks
• Inductive learning for product assortment graph completion
• Deep Constraint-based Propagation in Graph Neural Networks
• Graph Prolongation Convolutional Networks: Explicitly Multiscale Machine Learning on Graphs with Applications to Modeling of Cytoskeleton
• An Empirical Evaluation of Rewiring Approaches in Graph Neural Networks
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs
• Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis
• GraphGen-Redux: a Fast and Lightweight Recurrent Model for labeled Graph Generation
• Accelerating the identification of informative reduced representations of proteins with deep learning for graphs
• Network Representation Learning: From Traditional Feature Learning to Deep Learning
• A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring