The Graph Neural Network Model

  title={The Graph Neural Network Model},
  author={Franco Scarselli and Marco Gori and Ah Chung Tsoi and Markus Hagenbuchner and Gabriele Monfardini},
  journal={IEEE Transactions on Neural Networks},
Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. [] Key Method This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space.

Computational Capabilities of Graph Neural Networks

The functions that can be approximated by GNNs, in probability, up to any prescribed degree of precision are described, and includes most of the practically useful functions on graphs.

An Investigation Into Graph Neural Networks

GCN models can successfully process graph data and also outperforms traditional fully connected networks by 4% of classification accuracy, and it has proven that due to high interpretability, new architectures and libraries, and performance, there is a dramatic increase in applications and research of GNNs as a graphical analysis tool.

Dual Convolutional Neural Network for Graph of Graphs Link Prediction

A dual convolutional neural network is proposed that extracts node representations by combining the external and internal graph structures in an end-to-end manner.

Graph Neural Network: A Comprehensive Review on Non-Euclidean Space

This review provides a comprehensive overview of the state-of-the-art methods of graph-based networks from a deep learning perspective and formulates a systematic categorization of GNN models according to their applications from theory to real-life problems to encapsulate the importance of graph models.

Graph neural networks in node classification: survey and evaluation

This paper provides a comprehensive review about applying graph neural networks to the node classification task and discusses the state-of-the-art methods, divided into three main categories: convolutional mechanism, attention mechanism and autoencoder mechanism.

Dynamic Graph Neural Networks

DGNN is proposed, a new Dynamic Graph Neural Network model, which can model the dynamic information as the graph evolving and can keep updating node information by capturing the sequential information of edges, the time intervals between edges and information propagation coherently.

Random Walk Graph Neural Networks

A more intuitive and transparent architecture for graph-structured data, so-called Random Walk Graph Neural Network (RWNN), which consists of a number of trainable “hidden graphs” which are compared against the input graphs using a random walk kernel to produce graph representations.

Learning long-term dependencies using layered graph neural networks

This paper presents a new architecture, called Layered GNN (LGNN), realized by a cascade of GNNs: each layer is fed with the original data and with the state information calculated by the previous layer in the cascade, which allows each GNN to solve a subproblem.

GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks

This paper proposes GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method.



Computational Capabilities of Graph Neural Networks

The functions that can be approximated by GNNs, in probability, up to any prescribed degree of precision are described, and includes most of the practically useful functions on graphs.

Graph Neural Networks for Object Localization

The proposed learning framework provides a way to deal with complex data arising from image segmentation process, without exploiting any prior knowledge on the dataset, and proves the viability of the method and the effectiveness of the structural representation of images.

A new model for learning in graph domains

A new neural model, called graph neural network (GNN), capable of directly processing graphs, which extends recursive neural networks and can be applied on most of the practically useful kinds of graphs, including directed, undirected, labelled and cyclic graphs.

A Comparison between Recursive Neural Networks and Graph Neural Networks

An experimental comparison on an image classification problem is presented, showing that GNNs outperforms RNNs, and the main differences between the models are discussed w.r.t. their input domains, their approximation capabilities and their learning algorithms.

A general framework for adaptive processing of data structures

The framework described in this paper is an attempt to unify adaptive models like artificial neural nets and belief nets for the problem of processing structured information, where relations between data variables are expressed by directed acyclic graphs, where both numerical and categorical values coexist.

Document Mining Using Graph Neural Network

This paper applies the Graph Neural Network for the first time to a given learning task at an international competition on the classification of semi-structured documents and it will be shown that the performance significantly outperforms the results submitted by the best competitor.

The Principled Design of Large-Scale Recursive Neural Network Architectures--DAG-RNNs and the Protein Structure Prediction Problem

These methods are used to derive state-of-the-art predictors for protein structural features such as secondary structure and both fine- and coarse-grained contact maps and implications for the design of neural architectures are briefly discussed.

Neural Networks for Pattern Recognition

Supervised neural networks for the classification of structures

It is shown that neural networks can, in fact, represent and classify structured patterns and all the supervised networks developed for the classification of sequences can, on the whole, be generalized to structures.