Fast Haar transforms for graph neural networks

DOI10.1016/j.neunet.2020.04.028zbMath1468.68185arXiv1907.04786OpenAlexW3021853564WikidataQ95647866 ScholiaQ95647866MaRDI QIDQ1982431

Ming Li, Yu Guang Wang, Zheng Ma, Xiao-Sheng Zhuang

Publication date: 8 September 2021

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1907.04786

zbMATH Keywords

Haar basisgraph Laplaciangeometric deep learningfast Haar transformsgraph convolutiongraph neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50)

Related Items

Multi-view graph convolutional networks with attention mechanism, Adaptive directional Haar tight framelets on bounded domains for digraph signal representations, K-plex cover pooling for graph neural networks, Regularity properties of Haar frames, Unnamed Item

Uses Software

• MoleculeNet
• FastGCN
• DeepWalk

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• MoleculeNet
• FastGCN
• Wavelets on graphs via spectral graph theory
• Support-vector networks
• Tight framelets and fast framelet filter bank transforms on manifolds
• Representation of functions on big data: graphs and trees
• Representation of functions on big data associated with directed graphs
• Ten Lectures on Wavelets
• A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
• (Nearly) Sample-Optimal Sparse Fourier Transform
• Random forests