Redescription Model Mining

TL;DR

Redescription Model Mining is a new method that finds interpretable, similar patterns across two datasets with different attributes and no shared instances, revealing potential underlying phenomena.

Contribution

It combines Exceptional Model Mining and Redescription Mining to identify comparable models across datasets with limited shared information.

Findings

Developed interestingness measures for pattern selection

Proposed efficient algorithms for the new problem setting

Demonstrated potential on synthetic and real-world data

Abstract

This paper introduces Redescription Model Mining, a novel approach to identify interpretable patterns across two datasets that share only a subset of attributes and have no common instances. In particular, Redescription Model Mining aims to find pairs of describable data subsets -- one for each dataset -- that induce similar exceptional models with respect to a prespecified model class. To achieve this, we combine two previously separate research areas: Exceptional Model Mining and Redescription Mining. For this new problem setting, we develop interestingness measures to select promising patterns, propose efficient algorithms, and demonstrate their potential on synthetic and real-world data. Uncovered patterns can hint at common underlying phenomena that manifest themselves across datasets, enabling the discovery of possible associations between (combinations of) attributes that do not appear in the same dataset.