all AI news
Graph Neural Networks as Gradient Flows. (arXiv:2206.10991v1 [cs.LG])
June 23, 2022, 1:12 a.m. | Francesco Di Giovanni, James Rowbottom, Benjamin P. Chamberlain, Thomas Markovich, Michael M. Bronstein
stat.ML updates on arXiv.org arxiv.org
Dynamical systems minimizing an energy are ubiquitous in geometry and
physics. We propose a gradient flow framework for GNNs where the equations
follow the direction of steepest descent of a learnable energy. This approach
allows to explain the GNN evolution from a multi-particle perspective as
learning attractive and repulsive forces in feature space via the positive and
negative eigenvalues of a symmetric "channel-mixing" matrix. We perform
spectral analysis of the solutions and conclude that gradient flow graph
convolutional models can …
arxiv gradient graph graph neural networks lg networks neural networks
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
IT Commercial Data Analyst - ESO
@ National Grid | Warwick, GB, CV34 6DA
Stagiaire Data Analyst – Banque Privée - Juillet 2024
@ Rothschild & Co | Paris (Messine-29)
Operations Research Scientist I - Network Optimization Focus
@ CSX | Jacksonville, FL, United States
Machine Learning Operations Engineer
@ Intellectsoft | Baku, Baku, Azerbaijan - Remote
Data Analyst
@ Health Care Service Corporation | Richardson Texas HQ (1001 E. Lookout Drive)