all AI news
A Differential Geometric View and Explainability of GNN on Evolving Graphs
March 12, 2024, 4:42 a.m. | Yazheng Liu, Xi Zhang, Sihong Xie
cs.LG updates on arXiv.org arxiv.org
Abstract: Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction. Graphs can be evolving and it is vital to formally model and understand how a trained GNN responds to graph evolution. We propose a smooth parameterization of the GNN predicted distributions using axiomatic attribution, where the distributions are on a low-dimensional manifold within a high-dimensional embedding space. We exploit the differential geometric viewpoint to model distributional …
abstract art arxiv biochemistry cs.ai cs.lg differential evolution explainability gnn graph graph neural networks graphs networks neural networks prediction social social networks state state-of-the-art models type view vital
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Robotics Technician - 3rd Shift
@ GXO Logistics | Perris, CA, US, 92571