The Graph Neural Network Model
By Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, Gabriele Monfardini. 2009
9,596 citations recorded by the source corpus.
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. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. 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. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Graph Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Mohit Bansal
- Sergey Levine
- Quoc V. Le
- Percy Liang
- Jianfeng Gao
- Ruslan Salakhutdinov
- Kyunghyun Cho
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Ming-Hsuan Yang
- Jitendra Malik
- Bernt Schiele
- Andrew Zisserman
In Graph Learning
- William L. Hamilton
- Jure Leskovec
- Stephan Günnemann
- Rex Ying
- Matthias Fey
- Michael M. Bronstein
- Thomas Kipf
- Aleksandar Bojchevski
Citations in the corpus
- Semi-Supervised Classification with Graph Convolutional Networks (2016, methodology): “In the following, we consider a two-layer GCN for semi-supervised node classification on a graph with a symmetric adjacency matrix A (binary or weighted).”
- Graph Attention Networks (2017, background): “Graph Neural Networks (GNNs) were introduced in Gori et al. (2005) and Scarselli et al. (2009) as a generalization of recursive neural networks that can directly deal with a more general class of graphs, e.g. cyclic, directed and undirected graphs.”
- Inductive Representation Learning on Large Graphs (2017, neutral): “There are also a number of recent neural network approaches to supervised learning over graph structures [7, 10, 21, 31].”
- Object-Centric Learning with Slot Attention (2020, background): “[54] Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini.”
- Non-local Neural Networks (2017, methodology): “These methods and ours are also related to a more abstract model called graph neural networks [41].”
- Object-Centric Image Generation from Layouts (2020, methodology): “yer in an Inception-V3 network [55] pre-trained on the Imagenet dataset. We extract global visual features vG from the nal pooling layer. We encode the graph using a Graph Convolutional Network (GCN) [11,13,48] to obtain local graph features g j and apply a set of graph convolutions followed by a gr”
- Learning Convolutional Neural Networks for Graphs (2016, background): “We provide a brief introduction to the required background in convolutional networks and graph theory.”
- Gated Graph Sequence Neural Networks (2015, methodology): “Several variants are discussed in Scarselli et al. (2009) including positional graph forms, node-specific updates, and alternative representations of neighborhoods.”
- Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015, methodology): “Neural networks on input-dependent graphs [22] propose a neural network model for graphs having an interesting training procedure.”
- VAIN: Attentional Multi-agent Predictive Modeling (2017, neutral): “The seminal works in graph neural networks were presented by Scarselli et al. [12, 13] and Li et al. [14].”
- A simple neural network module for relational reasoning (2017, neutral): “Although several other models supporting relation-centric computation have been proposed, such as Graph Neural Neworks, Gated Graph Sequence Neural Netoworks, and Interaction Networks, [20, 13, 2], RNs are simpler, more exclusively focused on general relation reasoning, and easier to integrate withi”
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, neutral): “[19, 41].”
- Discriminative Embeddings of Latent Variable Models for Structured Data (2016, neutral): “Scarselli et al. (2009) proposed a neural network which generates features by solving a heuristic nonlinear system iteratively, and is learned using Almeida-Pineda algorithm.”
- Interaction Networks for Learning about Objects, Relations and Physics (2016, background): “The “graph neural network” [22] is a framework that shares learning 50 across nodes and edges, the “recursive autoencoder” [24] adapts its processing architecture to exploit 51 an input parse tree, the “neural programmer-interpreter” [21] is a composable neural network that 52 mimics the execution t”
- Directional Message Passing for Molecular Graphs (2020, neutral): “GNNs were first proposed in the 90s (Baskin et al., 1997; Sperduti & Starita, 1997) and 00s (Gori et al., 2005; Scarselli et al., 2009).”