GPNet: simplifying graph neural networks via multi-channel geometric polynomials

DOI10.1016/J.INS.2024.121696MaRDI QIDQ6669264zbMATH OpenFDO

Authors Xun Liu, Alex Hay-Man Ng, Fangyuan Lei, Yi-Kuan Zhang, Zhengming Li

Publication date 22 January 2025

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.INS.2024.121696

zbMATH Keywords

arbitrary graph filtersgeometric polynomialsgraph neural networksgraph-structured data

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• \(k\)-hop graph neural networks
• Theory of graph neural networks: representation and learning
• Revisiting graph neural networks from hybrid regularized graph signal reconstruction
• Polarized message-passing in graph neural networks

Cites work

• High-order graph attention network
• Multi-scale attributed node embedding

Cited in

(1)

• Polarized message-passing in graph neural networks

This page was built for publication: GPNet: simplifying graph neural networks via multi-channel geometric polynomials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6669264)