Machine Learning on Graphs: A Model and Comprehensive Taxonomy (2020-05-07T00:00:00.000000Z)

TL;DR

A comprehensive taxonomy of representation learning methods for graph-structured data is proposed, aiming to unify several disparate bodies of work and provide a solid foundation for understanding the intuition behind these methods, and enables future research in the area.

Abstract

There has been a surge of recent interest in learning representations for graph-structured data. Graph representation learning methods have generally fallen into three main categories, based on the availability of labeled data. The first, network embedding (such as shallow graph embedding or graph auto-encoders), focuses on learning unsupervised representations of relational structure. The second, graph regularized neural networks, leverages graphs to augment neural network losses with a regularization objective for semi-supervised learning. The third, graph neural networks, aims to learn differentiable functions over discrete topologies with arbitrary structure. However, despite the popularity of these areas there has been surprisingly little work on unifying the three paradigms. Here, we aim to bridge the gap between graph neural networks, network embedding and graph regularization models. We propose a comprehensive taxonomy of representation learning methods for graph-structured data, aiming to unify several disparate bodies of work. Specifically, we propose a Graph Encoder Decoder Model (GRAPHEDM), which generalizes popular algorithms for semi-supervised learning on graphs (e.g. GraphSage, Graph Convolutional Networks, Graph Attention Networks), and unsupervised learning of graph representations (e.g. DeepWalk, node2vec, etc) into a single consistent approach. To illustrate the generality of this approach, we fit over thirty existing methods into this framework. We believe that this unifying view both provides a solid foundation for understanding the intuition behind these methods, and enables future research in the area.

Authors

Ines Chami

4 papers

Sami Abu-El-Haija

3 papers

Bryan Perozzi

7 papers

TL;DR

Abstract

Authors

References172 items

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning

Pathfinder Discovery Networks for Neural Message Passing

Grale: Designing Networks for Graph Learning

Pure-Past Linear Temporal and Dynamic Logic on Finite Traces

Graph Clustering with Graph Neural Networks

Open Graph Benchmark: Datasets for Machine Learning on Graphs

Low-Dimensional Hyperbolic Knowledge Graph Embeddings

Graph Embedding with Personalized Context Distribution

Evaluating Logical Generalization in Graph Neural Networks

Convolutional Kernel Networks for Graph-Structured Data

Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs

Generalization and Representational Limits of Graph Neural Networks

Graph Representation Learning via Graphical Mutual Information Maximization

Hyperbolic Graph Neural Networks

Hyperbolic Graph Convolutional Neural Networks

On the Equivalence between Positional Node Embeddings and Structural Graph Representations

MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit

Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs

A Survey on Bias and Fairness in Machine Learning

What graph neural networks cannot learn: depth vs width

Spectral Clustering with Graph Neural Networks for Graph Pooling

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

On the equivalence between graph isomorphism testing and function approximation with GNNs

Position-aware Graph Neural Networks

Compositional Fairness Constraints for Graph Embeddings

Multi-relational Poincaré Graph Embeddings

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization

Graph U-Nets

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Stability and Generalization of Graph Convolutional Neural Networks

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

Self-Attention Graph Pooling

A survey on graph kernels

PyTorch-BigGraph: A Large-scale Graph Embedding System

Deep learning for molecular generation and optimization - a review of the state of the art

Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

Fast Graph Representation Learning with PyTorch Geometric

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

Graph Neural Networks: A Review of Methods and Applications

Deep Learning on Graphs: A Survey

Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon

Towards Sparse Hierarchical Graph Classifiers

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

How Powerful are Graph Neural Networks?

Invariant and Equivariant Graph Networks

Deep Graph Infomax

Learning Mixed-Curvature Representations in Product Spaces

Poincaré GloVe: Hyperbolic Word Embeddings

Riemannian Adaptive Optimization Methods

Enhanced Network Embeddings via Exploiting Edge Labels

Learning to Solve NP-Complete Problems - A Graph Neural Network for the Decision TSP

GEM: A Python package for graph embedding methods

A Tutorial on Network Embeddings

PADME: A Deep Learning-based Framework for Drug-Target Interaction Prediction

Hierarchical Graph Representation Learning with Differentiable Pooling

Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

Relational inductive biases, deep learning, and graph networks

MolGAN: An implicit generative model for small molecular graphs

NetLSD: Hearing the Shape of a Graph

Constrained Graph Variational Autoencoders for Molecule Design

An End-to-End Deep Learning Architecture for Graph Classification

Representation Tradeoffs for Hyperbolic Embeddings

Graphite: Iterative Generative Modeling of Graphs

GraphRNN: A Deep Generative Model for Graphs

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

Learning Deep Generative Models of Graphs

GEMSEC: Graph Embedding with Self Clustering

Junction Tree Variational Autoencoder for Molecular Graph Generation

Learning a SAT Solver from Single-Bit Supervision

GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders

Neural Graph Learning: Training Neural Networks Using Graphs

Network Representation Learning: A Survey

Few-Shot Learning with Graph Neural Networks