Incremental Constrained Clustering by Minimal Weighted Modification - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Incremental Constrained Clustering by Minimal Weighted Modification


Clustering is a well-known task in Machine Learning that aims at grouping instances according to their similarity. It is unsupervised and therefore difficult to tune without human input. In constrained clustering, subject matter experts (SME) can incorporate knowledge through constraints in the clustering algorithm. Involving an expert results in an incremental process where expert constraints are added on the fly, iteratively. Although satisfying the constraints is crucial, successive partitions should look alike to avoid disturbing the expert. In this paper, we present an incremental constrained clustering framework integrating active query strategies and a constraint programming model to fit the expert's expectations while preserving cluster structure, so that the user can understand the process and apprehend its impact. Our model supports instance and group-level constraints, which can be relaxed. Experiments on reference datasets and a case study related to the analysis of satellite image time series show the relevance of our framework.
Fichier principal
Vignette du fichier
CP'23 submission.pdf (4.51 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Licence : CC BY - Attribution

Dates and versions

hal-04158825 , version 1 (25-08-2023)





Aymeric Beauchamp, Thi-Bich-Hanh Dao, Samir Loudni, Christel Vrain. Incremental Constrained Clustering by Minimal Weighted Modification. CP 2023: 29th International Conference on Principles and Practice of Constraint Programming, Andre Augusto Cire, Aug 2023, Toronto, Ontario, Canada. ⟨10.4230/LIPIcs.CP.2023.10⟩. ⟨hal-04158825⟩
66 View
19 Download



Gmail Facebook X LinkedIn More