GraphMDL: Graph Pattern Selection based on Minimum Description Length - Archive ouverte HAL Access content directly
Conference Papers Year :

GraphMDL: Graph Pattern Selection based on Minimum Description Length

(1) , (1) , (1)
1

Abstract

Many graph pattern mining algorithms have been designed to identify recurring structures in graphs. The main drawback of these approaches is that they often extract too many patterns for human analysis. Recently, pattern mining methods using the Minimum Description Length (MDL) principle have been proposed to select a characteristic subset of patterns from transactional, sequential and relational data. In this paper, we propose an MDL-based approach for selecting a characteristic subset of patterns on labeled graphs. A key notion in this paper is the introduction of ports to encode connections between pattern occurrences without any loss of information. Experiments show that the number of patterns is drastically reduced. The selected patterns have complex shapes and are representative of the data.
Fichier principal
Vignette du fichier
ida_graphmdl.pdf (396.78 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02510517 , version 1 (17-03-2020)

Identifiers

  • HAL Id : hal-02510517 , version 1

Cite

Francesco Bariatti, Peggy Cellier, Sébastien Ferré. GraphMDL: Graph Pattern Selection based on Minimum Description Length. IDA 2020 - Symposium on Intelligent Data Analysis, Apr 2020, Konstanz, Germany. ⟨hal-02510517⟩
269 View
246 Download

Share

Gmail Facebook Twitter LinkedIn More