Transferability of spectral graph convolutional neural networks

MaRDI QIDQ5053307zbMATH OpenFDO

Authors Wei Huang, Lorenzo Bucci, Michael M. Bronstein, Gitta Kutyniok, Ron Levie

Publication date 6 December 2022

Full work available at URL https://arxiv.org/abs/1907.12972, https://jmlr.csail.mit.edu/papers/v22/20-213.html

zbMATH Keywords

generalizationgraph convolutional neural networkspectral methodstabilitytransferability

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Transferability of graph neural networks: an extended graphon approach
• Graph convolutional neural networks via scattering
• Complex exponential graph convolutional networks
• Wavelets on graphs via spectral graph theory
• Convolutional persistence transforms

Cites work

• Autoregressive Moving Average Graph Filtering
• CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
• Convergent sequences of dense graphs. I: Subgraph frequencies, metric properties and testing
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Discrete Signal Processing on Graphs: Sampling Theory
• Filtering Random Graph Processes Over Random Time-Varying Graphs
• Graph convolutional neural networks via scattering
• Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing
• Limits of dense graph sequences
• Optimal Graph-Filter Design and Applications to Distributed Linear Network Operators
• Random sampling of bandlimited signals on graphs
• Sampling of Graph Signals With Successive Local Aggregations
• Signals on Graphs: Uncertainty Principle and Sampling
• Sobolev spaces and harmonic maps for metric space targets
• Spectral stability of metric-measure Laplacians
• Stability Properties of Graph Neural Networks

Cited in

(8)

• Transferability of graph neural networks: an extended graphon approach
• CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
• Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms
• Complex exponential graph convolutional networks
• Theory of graph neural networks: representation and learning
• Two subspace methods for frequency sparse graph signals
• Generalization bounds for message passing networks on mixture of graphons
• Convergence of message-passing graph neural networks with generic aggregation on large random graphs

Describes a project that uses

Uses Software

• CayleyNets

This page was built for publication: Transferability of spectral graph convolutional neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5053307)