Polynomial-based graph convolutional neural networks for graph classification

DOI10.1007/S10994-021-06098-0MaRDI QIDQ2163182zbMATH OpenOpenAlexFDO

Authors Luca Pasa, Nicolò Navarin, Alessandro Sperduti

Publication date 10 August 2022

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-021-06098-0

zbMATH Keywords

deep learningstructured datagraph convolutional networksgraph neural networkmachine learning on graphs

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Fundamental Limits of Deep Graph Convolutional Networks for Graph Classification
• Graph deconvolutional networks
• Graph neural network
• Graph neural networks induced by concept lattices for classification
• Graph convolutional neural networks via scattering
• Graph neural networks: foundations, frontiers, and applications
• Convolutional Neural Network Architectures for Signals Supported on Graphs

Cites work

• A gentle introduction to deep learning for graphs
• Evaluating learning algorithms. A classification perspective
• Weisfeiler-Lehman graph kernels

Cited in

(3)

• CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
• Graph neural networks induced by concept lattices for classification
• Neural predictor-based automated graph classifier framework

Describes a project that uses

Uses Software

• SIGN
• Adam
• PyTorch
• AFGen

This page was built for publication: Polynomial-based graph convolutional neural networks for graph classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2163182)