The paper reviews a three-axis evaluation framework (stability, cluster quality, topological shape preservation) for Mapper algorithms, analyzes variants on synthetic and UCI Digits data, and finds the axes often conflict with no single variant optimal across all.
Ball mapper: a shape summary for topological data analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Topological data analysis provides a collection of tools to encapsulate and summarize the shape of data. Currently it is mainly restricted to \emph{mapper algorithm} and \emph{persistent homology}. In this paper we introduce new mapper--inspired descriptor that can be applied for exploratory data analysis.
fields
math.AT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Three Axis Evaluation Framework for Mapper Algorithms
The paper reviews a three-axis evaluation framework (stability, cluster quality, topological shape preservation) for Mapper algorithms, analyzes variants on synthetic and UCI Digits data, and finds the axes often conflict with no single variant optimal across all.