SHACUN: semi-supervised hierarchical active clustering based on ranking constraints

Authors:
Eya Ben Ahmed;Ahlem Nabli;Faïez Gargouri
Affiliations:
University of Sfax, Tunisia;University of Sfax, Tunisia;University of Sfax, Tunisia
Venue:
ICDM'12 Proceedings of the 12th Industrial conference on Advances in Data Mining: applications and theoretical aspects
Year:
2012

Citing 12
Cited 1

Algorithms for clustering data

Algorithms for clustering data
Bayesian Network Classifiers

Machine Learning - Special issue on learning with probabilistic representations
Induction of Decision Trees

Machine Learning
From Instance-level Constraints to Space-Level Constraints: Making the Most of Prior Knowledge in Data Clustering

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
The Case against Accuracy Estimation for Comparing Induction Algorithms

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
HISSCLU: a hierarchical density-based method for semi-supervised clustering

EDBT '08 Proceedings of the 11th international conference on Extending database technology: Advances in database technology
User Oriented Hierarchical Information Organization and Retrieval

ECML '07 Proceedings of the 18th European conference on Machine Learning
An active learning framework for semi-supervised document clustering with language modeling

Data & Knowledge Engineering
Using instance-level constraints in agglomerative hierarchical clustering: theoretical and empirical results

Data Mining and Knowledge Discovery
Which clustering do you want? inducing your ideal clustering with minimal feedback

Journal of Artificial Intelligence Research
On the effects of constraints in semi-supervised hierarchical clustering

ANNPR'06 Proceedings of the Second international conference on Artificial Neural Networks in Pattern Recognition
Hierarchical confidence-based active clustering

Proceedings of the 27th Annual ACM Symposium on Applied Computing

A new semi-supervised hierarchical active clustering based on ranking constraints for analysts groupization

Applied Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Semi-supervised approaches have proven to be efficient in clustering tasks. They allow user input, thus enhancing the quality of the clustering. However, the user intervention is generally limited to integrate boolean constraints in form of must-link and cannot-link constraints between pairs of objects. This paper investigates the issue of satisfying ranked constraints in performing hierarchical clustering. $\mathcal{SHACUN}$ is a new introduced method for handling cases when some constraints are more important than others and must be firstly enforced. Carried out experiments on real log files used for decision-maker groupization in data warehouse confirm the soundness of our approach.