Convolutional Neural Network Architectures for Signals Supported on Graphs
By Fernando Gama, Antonio Garcia Marques, Geert Leus, Alejandro Ribeiro. IEEE Transactions on Signal Processing, 2018
318 citations recorded by the source corpus.
Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and reinterprets pooling as a possibly nonlinear subsampling stage where nearby nodes pool their information in a set of preselected sample nodes. A key component of the architecture is to remember the position of sampled nodes to permit computation of convolutional features at deeper layers. The second architecture, dubbed aggregation GNN, diffuses the signal through the graph and stores the sequence of diffused components observed by a designated node. This procedure effectively aggregates all components into a stream of information having temporal structure to which the convolution and pooling stages of regular CNNs can be applied. A multinode version of aggregation GNNs is further introduced for operation in large-scale graphs. An important property of selection and aggregation GNNs is that they reduce to conventional CNNs when particularized to time signals reinterpreted as graph signals in a circulant graph. Comparative numerical analyses are performed in a source localization application over synthetic and real-world networks. Performance is also evaluated for an authorship attribution problem and text category classification. Multinode aggregation GNNs are consistently the best-performing GNN architecture.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/c7465f55170e472bc2eb0e40143de5e6475821d7
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
- Alejandro Ribeiro
- Fernando Gama
- Amanda Prorok
- Qingbiao Li
- Damian Owerko
- Georgios B. Giannakis
- Aryan Mokhtari
- Simon Lacoste-Julien
In Statistical and Nonlinear Physics
Citations in the corpus
- Graph Neural Networks for Decentralized Multi-Robot Path Planning (2019, methodology): “For each panel, we train a model for N ∈ [4, 6, 8, 10, 12], and test it on instances of the same robot team size.”
- Optimal Power Flow Using Graph Neural Networks (2019, methodology): “In particular, we focus on graph neural networks (GNNs) [13–15] to exploit their stability properties [21] that guarantee scalability [22,23].”