A new model for learning in graph domains

By Marco Gori, Gabriele Monfardini, Franco Scarselli. 2005

2,171 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, 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

In Computational Theory and Mathematics

In Graph Learning

Citations in the corpus

Semi-Supervised Classification with Graph Convolutional Networks (2016, background): “the process of learning embeddings, thereby removing one step from the aforementioned pipeline. 4.2 NEURAL NETWORKS ON GRAPHS Neural networks that operate on graphs have previously been introduced in Gori et al. (2005); Scarselli et al. (2009) as a form of recurrent neural network. Their framework r”
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 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”
Gated Graph Sequence Neural Networks (2015, methodology): “More closely related to our goal in this work are methods that learn features on graphs, including Graph Neural Networks (Gori et al., 2005; Scarselli et al., 2009), spectral networks (Bruna et al., 2013) and recent work on learning graph ﬁngerprints for classiﬁcation tasks on graph representations ”
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].”
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, neutral): “[19, 41].”
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving (2019, methodology): “We begin by viewing the Transformer as a kind of Graph Neural Network (e.g., Gori et al., 2005).”
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).”
Graph Convolutional Neural Networks for Web-Scale Recommender Systems (2018, background): “(2005) [15] and further elaborated on in Scarselli et al.”
Auto-GNN: Neural architecture search of graph neural networks (2019, methodology): “the output value in each graph convolutional layer of GNN architecture. Suppose that we have parameters deeply trained in a layer with Sigmoid activation function, bounding the output within interval [0,1]. If we transfer the parameter to another layer possessing Linear function, the output value ma”
On the Binding Problem in Artificial Neural Networks (2020, methodology): “MPNNs were initially conceived as a generalization of RNNs to graph-structured inputs (Sperduti and Starita, 1997; Gori et al., 2005) and have since been adapted to consider modern deep neural networks (Li et al.”
Relational inductive biases, deep learning, and graph networks (2018, background): “Models in the graph neural network family (Gori et al., 2005; Scarselli et al., 2005, 2009a; Li et al., 2016) have been explored in a diverse range of problem domains, across supervised, semi-supervised, unsupervised, and reinforcement learning settings.”
The More You Know: Using Knowledge Graphs for Image Classification (2016, methodology): “There has been a lot of work in end-to-end learning on graphs or neural network trained on graphs [31, 2, 6, 11, 25, 22, 9, 21].”
Representation Learning on Graphs: Methods and Applications (2017, methodology): “In the original GNN framework [25, 51] every node, v i , is initialized with a random embedding, h 0 i (node attributes are ignored), and at each iteration of the GNN algorithm nodes accumulate inputs from their neighbors using simple neural network layers: where W ∈ R d × d and b ∈ R d are…”
Learning Graph-Level Representation for Drug Discovery (2017, background): “Graph-based Neural networks have previously introduced in(Gori, Monfardini, and Scarselli 2005; Scarselli et al. 2009) as a form of recurrent neural network.”
Graph Normalizing Flows (2019, background): “Machine learning has recently turned its attention to modeling graph-structured data using graph neural networks (GNNs) [8, 23, 16, 13, 6] that can exploit the structure of relational systems to create more accurate and generalizable predictions.”