Data mining: concepts and techniques
Data mining: concepts and techniques
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Architecture of Cognition
MQSearch: image search by multi-class query
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Useful clustering outcomes from meaningful time series clustering
AusDM '07 Proceedings of the sixth Australasian conference on Data mining and analytics - Volume 70
SSPS: A Semi-Supervised Pattern Shift for Classification
Neural Processing Letters
Semisupervised kernel matrix learning by kernel propagation
IEEE Transactions on Neural Networks
Graph transduction as a non-cooperative game
GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
A novel ant-based clustering algorithm using the kernel method
Information Sciences: an International Journal
Multiple-Instance learning via random walk
ECML'06 Proceedings of the 17th European conference on Machine Learning
Graph transduction as a noncooperative game
Neural Computation
iVAT and aVAT: enhanced visual analysis for cluster tendency assessment
PAKDD'10 Proceedings of the 14th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining - Volume Part I
| Hi-index | 0.00 |
Clustering aims to find useful hidden structures in data. In this paper we present a new clustering algorithm that builds upon the consistency method (Zhou, et.al., 2003), a semi-supervised learning technique with the property of learning very smooth functions with respect to the intrinsic structure revealed by the data. Other methods, e.g. Spectral Clustering, obtain good results on data that reveals such a structure. However, unlike Spectral Clustering, our algorithm effectively detects both global and within-class outliers, and the most representative examples in each class. Furthermore, we specify an optimization framework that estimates all learning parameters, including the number of clusters, directly from data. Finally, we show that the learned cluster-models can be used to add previously unseen points to clusters without re-learning the original cluster model. Encouraging experimental results are obtained on a number of real world problems.