Intrinsic Dimension for Large-Scale Geometric Learning

by   Maximilian Stubbemann, et al.
Universität Kassel

The concept of dimension is essential to grasp the complexity of data. A naive approach to determine the dimension of a dataset is based on the number of attributes. More sophisticated methods derive a notion of intrinsic dimension (ID) that employs more complex feature functions, e.g., distances between data points. Yet, many of these approaches are based on empirical observations, cannot cope with the geometric character of contemporary datasets, and do lack an axiomatic foundation. A different approach was proposed by V. Pestov, who links the intrinsic dimension axiomatically to the mathematical concentration of measure phenomenon. First methods to compute this and related notions for ID were computationally intractable for large-scale real-world datasets. In the present work, we derive a computationally feasible method for determining said axiomatic ID functions. Moreover, we demonstrate how the geometric properties of complex data are accounted for in our modeling. In particular, we propose a principle way to incorporate neighborhood information, as in graph data, into the ID. This allows for new insights into common graph learning procedures, which we illustrate by experiments on the Open Graph Benchmark.


page 1

page 2

page 3

page 4


Observing the Population Dynamics in GE by means of the Intrinsic Dimension

We explore the use of Intrinsic Dimension (ID) for gaining insights in h...

Estimating the effective dimension of large biological datasets using Fisher separability analysis

Modern large-scale datasets are frequently said to be high-dimensional. ...

Estimating the intrinsic dimension of datasets by a minimal neighborhood information

Analyzing large volumes of high-dimensional data is an issue of fundamen...

Intrinsic dimension estimation for discrete metrics

Real world-datasets characterized by discrete features are ubiquitous: f...

Intrinsic dimension estimation for locally undersampled data

High-dimensional data are ubiquitous in contemporary science and finding...

Intrinsic dimension and its application to association rules

The curse of dimensionality in the realm of association rules is twofold...

The geometry of hidden representations of large transformer models

Large transformers are powerful architectures for self-supervised analys...

Please sign up or login with your details

Forgot password? Click here to reset