Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 28 references that are in the map. First posted on arXiv 1 Sep 2023.
Builds on
9 of 28 references.
References · 9
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 359
- 2017Stochastic gradient descent performs variational inference, converges to limit cycles for deep networkscited by 109
- 2020Superpixel Image Classification with Graph Attention Networkscited by 20
- 2018MoNet: Moments Embedding Networkcited by 4
- 2019A geometric interpretation of stochastic gradient descent using diffusion metricscited by 1
Built on by
Not cited yet.