MindMiner: A Mixed-Initiative Interface for Interactive Distance Metric Learning

Abstract : We present MindMiner, a mixed-initiative interface for capturing subjective similarity measurements via a combination of new interaction techniques and machine learning algorithms. MindMiner collects qualitative, hard to express similarity measurements from users via active polling with uncertainty and example based visual constraint creation. MindMiner also formulates human prior knowledge into a set of inequalities and learns a quantitative similarity distance metric via convex optimization. In a 12-subject peer-review understanding task, we found MindMiner was easy to learn and use, and could capture users’ implicit knowledge about writing performance and cluster target entities into groups that match subjects’ mental models. We also found that MindMiner’s constraint suggestions and uncertainty polling functions could improve both efficiency and the quality of clustering.
Type de document :
Communication dans un congrès
15th Human-Computer Interaction (INTERACT), Sep 2015, Bamberg, Germany. Lecture Notes in Computer Science, LNCS-9297 (Part II), pp.611-628, 2015, Human-Computer Interaction – INTERACT 2015. 〈10.1007/978-3-319-22668-2_47〉
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01599869
Contributeur : Hal Ifip <>
Soumis le : lundi 2 octobre 2017 - 15:41:38
Dernière modification le : mardi 3 octobre 2017 - 14:45:26

Fichier

346942_1_En_47_Chapter.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Xiangmin Fan, Youming Liu, Nan Cao, Jason Hong, Jingtao Wang. MindMiner: A Mixed-Initiative Interface for Interactive Distance Metric Learning. 15th Human-Computer Interaction (INTERACT), Sep 2015, Bamberg, Germany. Lecture Notes in Computer Science, LNCS-9297 (Part II), pp.611-628, 2015, Human-Computer Interaction – INTERACT 2015. 〈10.1007/978-3-319-22668-2_47〉. 〈hal-01599869〉

Partager

Métriques

Consultations de la notice

19

Téléchargements de fichiers

8