The Minimum Description Length Principle for Pattern Mining: A Survey

TL;DR

This survey reviews how the Minimum Description Length (MDL) principle is applied to pattern mining, emphasizing its role in selecting compact, high-quality pattern sets through information-theoretic methods.

Contribution

It provides a comprehensive overview of MDL-based pattern mining methods, connecting theoretical foundations with practical applications across data types.

Findings

MDL promotes compact, high-quality pattern sets.

Various MDL-based algorithms have been developed for different data types.

Open issues and future directions in MDL pattern mining are discussed.

Abstract

This is about the Minimum Description Length (MDL) principle applied to pattern mining. The length of this description is kept to the minimum. Mining patterns is a core task in data analysis and, beyond issues of efficient enumeration, the selection of patterns constitutes a major challenge. The MDL principle, a model selection method grounded in information theory, has been applied to pattern mining with the aim to obtain compact high-quality sets of patterns. After giving an outline of relevant concepts from information theory and coding, as well as of work on the theory behind the MDL and similar principles, we review MDL-based methods for mining various types of data and patterns. Finally, we open a discussion on some issues regarding these methods, and highlight currently active related data analysis problems.