Intrinsic Dimensionality and Graph Learning

Tuesday, September 19, 2023

4.00 p.m

ISI Foundation 1st floor

Maximilian Stubbemann, Knowledge and Data Engineering Group, University of Kassel

In this talk, we present our recent work regarding the computation of intrinsic dimensionalities of large-scale datasets. Our work builds on an axiomatization  by V. Pestov and its adaption to geometric datasets by Hanika et al. We will explain how we made this concept measurable for datasets with hundred millions of data points. Furthermore, we will discuss how this concept can be applied to the realm of graph learning. For this, we study how the intrinsic dimensionality of graph data  is connected to the success of classification via graph neural networks.