Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks

09/01/2023

∙

We examine a Geometric Deep Learning model as a thermodynamic system treating the weights as non-quantum and non-relativistic particles. We employ the notion of temperature previously defined in [7] and study it in the various layers for GCN and GAT models. Potential future applications of our findings are discussed.

READ FULL TEXT

Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks

Geometric deep learning approach to knot theory

Comparison between ARIMA and Deep Learning Models for Temperature Forecasting

Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networks

Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric

Torsion Graph Neural Networks

Deep Learning and Geometric Deep Learning: an introduction for mathematicians and physicists

On the use of graph neural networks and shape-function-based gradient computation in the deep energy method

Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks

Related Research

Geometric deep learning approach to knot theory

Comparison between ARIMA and Deep Learning Models for Temperature Forecasting

Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networks

Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric

Torsion Graph Neural Networks

Deep Learning and Geometric Deep Learning: an introduction for mathematicians and physicists

On the use of graph neural networks and shape-function-based gradient computation in the deep energy method