Fixed and adaptive landmark sets for finite pseudometric spaces

TL;DR

This paper introduces 'lastfirst', a new landmark sampling method for topological data analysis that handles variable density and multiplicities better than existing methods, improving biomedical data analysis.

Contribution

The paper defines and proves properties of 'lastfirst', a landmark sampling procedure based on ranked distances, and compares it to maxmin in biomedical data tasks.

Findings

Lastfirst outperforms maxmin in homology detection.

Lastfirst achieves comparable results in feature detection and class prediction.

Lastfirst is applicable to any data with arbitrary pairwise distances.

Abstract

Topological data analysis (TDA) is an expanding field that leverages principles and tools from algebraic topology to quantify structural features of data sets or transform them into more manageable forms. As its theoretical foundations have been developed, TDA has shown promise in extracting useful information from high-dimensional, noisy, and complex data such as those used in biomedicine. To improve efficiency, these techniques may employ landmark samplers. The heuristic maxmin procedure obtains a roughly even distribution of sample points by implicitly constructing a cover comprising sets of uniform radius. However, issues arise with data that vary in density or include points with multiplicities, as are common in biomedicine. We propose an analogous procedure, "lastfirst" based on ranked distances, which implies a cover comprising sets of uniform cardinality. We first rigorously define the procedure and prove that it obtains landmarks with desired properties. We then perform benchmark tests and compare its performance to that of maxmin, on feature detection and class prediction tasks involving simulated and real-world biomedical data. Lastfirst is more general than maxmin in that it can be applied to any data on which arbitrary (and not necessarily symmetric) pairwise distances can be computed. Lastfirst is more computationally costly, but our implementation scales at the same rate as maxmin. We find that lastfirst achieves comparable performance on prediction tasks and outperforms maxmin on homology detection tasks. Where the numerical values of similarity measures are not meaningful, as in many biomedical contexts, lastfirst sampling may also improve interpretability.