Vertical collaborative clustering using generative topographic maps - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Vertical collaborative clustering using generative topographic maps

(1) , , (2) , (1)
1
2

Abstract

Collaborative clustering is a recent field of Machine Learning that shows similarities with both transfer learning and ensemble learning. It uses two-step approaches where different clustering algorithms first process data individually and then exchange their information and results with a goal of mutual improvement. In this article, we introduce a new collaborative learning approach based on collaborative clustering principles and applied to the Generative Topographic Mapping (GTM) algorithm. Our method consists in applying the GTM algorithm on different data sets where similar clusters can be found (same feature spaces and similar data distributions), and then to use a collaborative framework on the generated maps with the goal of transferring knowledge between them. The proposed approach has been validated on several data sets, and the experimental results have shown very promising performances.
Not file

Dates and versions

hal-01589449 , version 1 (18-09-2017)

Identifiers

Cite

Jérémie Sublime, Nistor Grozavu, Younes Bennani, Antoine Cornuéjols. Vertical collaborative clustering using generative topographic maps. 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR), Nov 2015, Fukuoka, Japan. pp.199-204, ⟨10.1109/SOCPAR.2015.7492807⟩. ⟨hal-01589449⟩
101 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More