Geometric deep learning: a temperature based analysis of graph neural networks

DOI10.1007/978-3-031-38299-4_65MaRDI QIDQ6179069zbMATH OpenOpenAlexFDO

Authors M. Lapenna, Francesco Faglioni, Ferdinando Zanchetta, Rita Fioresi

Publication date 16 January 2024

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2309.00699

zbMATH Keywords

geometric deep learningmachine learningstatistical mechanics

Mathematics Subject Classification ID

Graph theory (including graph drawing) in computer science (68R10) Artificial neural networks and deep learning (68T07) Equilibrium statistical mechanics (82B99)

Recommendations

• Theory of graph neural networks: representation and learning
• Understanding the message passing in graph neural networks via power iteration clustering
• A charge-preserving method for solving graph neural diffusion networks
• The logic of graph neural networks

Cites work

• An efficient learning procedure for deep Boltzmann machines
• Contact geometry for simple thermodynamical systems with friction
• Entropy-SGD: biasing gradient descent into wide valleys
• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• Information Theory and Statistical Mechanics
• Neurons with graded response have collective computational properties like those of two-state neurons
• On the thermodynamic interpretation of deep learning systems
• The Fokker-Planck equation. Methods of solutions and applications.

Cited in

(4)

• Geometric deep learning for design of catalysts and molecules
• On the Explainability of Graph Convolutional Network With GCN Tangent Kernel
• A charge-preserving method for solving graph neural diffusion networks
• Preface to the special issue on geometric science of information (GSI'23)

This page was built for publication: Geometric deep learning: a temperature based analysis of graph neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6179069)