Open AccessPosted Content
Machine Learning on Graphs: A Model and Comprehensive Taxonomy
Reads0
Chats0
TLDR
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.read more
Citations
More filters
Posted Content
Graph Neural Networks: A Review of Methods and Applications
Jie Zhou,Ganqu Cui,Shengding Hu,Zhengyan Zhang,Cheng Yang,Zhiyuan Liu,Lifeng Wang,Changcheng Li,Maosong Sun +8 more
TL;DR: A detailed review over existing graph neural network models is provided, systematically categorize the applications, and four open problems for future research are proposed.
Journal ArticleDOI
Graph Neural Networks: A Review of Methods and Applications
Jie Zhou,Ganqu Cui,Shengding Hu,Zhengyan Zhang,Cheng Yang,Zhiyuan Liu,Lifeng Wang,Changcheng Li,Maosong Sun +8 more
TL;DR: In this paper, the authors propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.
Posted Content
Benchmarking Graph Neural Networks
TL;DR: A reproducible GNN benchmarking framework is introduced, with the facility for researchers to add new models conveniently for arbitrary datasets, and a principled investigation into the recent Weisfeiler-Lehman GNNs (WL-GNNs) compared to message passing-based graph convolutional networks (GCNs).
Journal Article
Benchmarking Graph Neural Networks
TL;DR: A reproducible GNN benchmarking framework is introduced, with the facility for researchers to add new models conveniently for arbitrary datasets, and a principled investigation into the recent Weisfeiler-Lehman GNNs (WL-GNNs) compared to message passing-based graph convolutional networks (GCNs).
Posted Content
TUDataset: A collection of benchmark datasets for learning with graphs.
Christopher Morris,Nils M. Kriege,Franka Bause,Kristian Kersting,Petra Mutzel,Marion Neumann +5 more
TL;DR: The TUDataset for graph classification and regression is introduced, which consists of over 120 datasets of varying sizes from a wide range of applications and provides Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools.
References
More filters
Proceedings Article
Constrained Graph Variational Autoencoders for Molecule Design
TL;DR: A variational autoencoder model in which both encoder and decoder are graph-structured is proposed and it is shown that by using appropriate shaping of the latent space, this model allows us to design molecules that are (locally) optimal in desired properties.
Proceedings Article
Poincaré GloVe: Hyperbolic Word Embeddings
TL;DR: The authors proposed to embed words in a Cartesian product of hyperbolic spaces which they theoretically connect to the Gaussian word embeddings and their Fisher geometry, and applied the well-known Glove algorithm to learn unsupervised word embedding in this type of Riemannian manifold.
Proceedings Article
What graph neural networks cannot learn: depth vs width
TL;DR: GNNmp are shown to be Turing universal under sufficient conditions on their depth, width, node attributes, and layer expressiveness, and it is discovered that GNNmp can lose a significant portion of their power when their depth and width is restricted.
Posted Content
Learning a SAT Solver from Single-Bit Supervision
TL;DR: NeuroSAT as discussed by the authors is a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability, which can solve problems that are substantially larger and more difficult than it ever saw during training by simply running for more iterations.
Proceedings Article
Hyperbolic Graph Convolutional Neural Networks.
TL;DR: This work proposes Hyperbolic Graph Convolutional Neural Network (HGCN), the first inductive hyperbolic GCN that leverages both the expressiveness of GCNs andhyperbolic geometry to learn inductive node representations for hierarchical and scale-free graphs.