Neural Network for Graphs: A Contextual Constructive Approach

By Alessio Micheli. 2009

663 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering, Natural Language Processing, 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 Cognitive Neuroscience

In Electrical and Electronic Engineering

In Natural Language Processing

In Graph Learning

Citations in the corpus

Gated Graph Sequence Neural Networks (2015, background): “Micheli (2009) proposed another closely related model that differs from GNNs mainly in the output model.”
Diffusion-Convolutional Neural Networks (2015, background): “A related branch of work that has focused on extending convolutional neural networks to domains where the structure of the graph itself is of direct interest [13, 14, 15].”
Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015, background): “[16] also propose a neural network model for graphs with a learning scheme whose inner loop optimizes not the training loss, but rather the correlation between each newly-proposed vector and the training error residual.”
Neural Message Passing for Quantum Chemistry (2017, methodology): “While neural networks have been applied in a variety of situations (Merkwirth & Lengauer, 2005; Micheli, 2009; Lusci et al., 2013; Duvenaud et al., 2015), they have yet to become widely adopted.”
Auto-GNN: Neural architecture search of graph neural networks (2019, background): “Graph neural networks (GNNs) (Micheli, 2009) have emerged as predominant tools to model graph data at various domains, such as social media (Grover and Leskovec, 2016) and bioinformatics (Zitnik and Leskovec, 2017).”
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].”
Molecular graph convolutions: moving beyond fingerprints (2016, background): “Similarly, Micheli [22] presents a more general formulation of the same concept of iterated local information transfer across edges and applies this method to predicting the boiling point of alkanes.”
Pre-training Graph Neural Networks with Kernels (2018, neutral): “While Micheli [2009] adopts Cascade-Correlation for training, Duvenaud et al. [2015] uses an end-to-end back-propagation.”
A Comprehensive Survey on Graph Neural Networks (2019, background): “Neural Network for Graphs (NN4G) [24], proposed in parallel with GNN*, is the ﬁrst work towards spatial-based ConvGNNs.”
Smart Contract Vulnerability Detection using Graph Neural Network (2020, background): “[Micheli, 2009] directly sums up a node’s neighborhood information for graph convolutions, while recent work [ Veliˇckovi´c et al. , 2017 ] and [ Zhang et al. , 2018 ] learn different weights of neighboring nodes using attention mechanisms.”
A Survey on Vision--Language--Action Models for Embodied AI (2024, positive): “Neural Network for Graphs (NN4G) [317] is the first spatial network.”
Deconfounded Image Captioning: A Causal Retrospect (2020, methodology): “Inspired by this, researchers [44], [45], [46] proposed to learn a scene graph from the image and to apply Graph Neural Network [47], [48], [49] to transform this Fig.”
AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing (2019, background): “In the past decade, work has continued on optimizing GNN algorithms exploring new neural network approaches [8], [19], [20], [22]–[25].”
A Survey on Deep Learning (2018, background): “Another alternative is to use the incremental approaches that exploit medium and large datasets on offline training [109].”
On Filter Size in Graph Convolutional Networks (2018, methodology): “However, one of the core components, the graph convolution, has not changed much with respect to the earlier works [8], [9].”
Evolutionary Architecture Search for Graph Neural Networks (2020, methodology): “irregular in that network nodes may have different numbers of unordered neighborhoods [3], causing the failure of existing neural models such as CNN and RNN in the graph domain [18], [19].”
Graph Neural Networks With Convolutional ARMA Filters (2019, neutral): “…graph to learn nodes/graph embeddings (Perozzi et al., 2014; Duvenaud et al., 2015; Yang et al., 2016; Hamilton et al., 2017; Bac-ciu et al., 2018), or to directly perform inference tasks by mapping the node features into categorical labels or real values (Scarselli et al., 2009; Micheli, 2009).”