|
Schedule
Opening Session
8:45 Introduction
8:55 Invited Talk: Matthias Seeger
A Taxonomy for Semi-supervised Learning Methods
9:40 - Session: Graph based semi-supervised learning
9:40 - 10:00 Person identification in webcam images: An application of semi-supervised learning
Maria-Florina Balcan, Avrim Blum, Patrick Pakyan Choi, John Lafferty, Brian Pantano, Mugizi R. Rwebangira, and Xiaojin Zhu
10:00 - 10:20 Semi-supervised learning with sparse grids
Jochen Garcke and Michael Griebel
10:20 - 10:40 Blockwise Supervised Inference on Large Graphs
Kai Yu, Shipeng Yu, and Volker Tresp
10:40 - 11:10 Coffee break
11:10 - Session: Low density separation techniques
11:10 - 11:30 RBF Networks for learning from partially labeled data
Abdelhamid Bouchachia
11:30 - 11:50 Learning with partially labeled data - with confidence
Eric Gaussier, and Cyril Goutte
11:50 - 12:10 Performance comparisons of semi-supervised learning algorithms
Te M. Huang and Vojislav Kecman
12:10 - 14:10 Lunch
14:10 - 14:55 Second Invited Talk: Zoubin Ghahramani
Graph-based and Bayesian approaches to semi-supervised learning
14:55 - Session: Semi-supervised Learning criteria
14:55 - 15:15 Semi-supervised learning - a statistical physics approach
Gad Getz, Noam Shental, and Eytan Domany
15:15 - 15:30 Splitting the unsupervised and supervised components of semi-supervised learning
Clayton S. Oliveira, Fabio G. Cozman, and Ira Cohen
15:30 - 16:00 Coffee break
16:00 - Session: Applications
16:00 - 16:15 A Sampling technique for efficiently estimating measures of query retrieval performance using incomplete judgments
Javed A. Aslam, Virgil Pavlu, and Emine Yilmaz
16:15 - 16:30 Improving kernel classifiers for object categorisation problems
Alexei Pozdnoukhov and Samy Bengio
16:30 - 16:45 Linear Manifold regularisation for large scale semi-supervised learning
Vikas Sindhwani, Partha Niyogi, Mikhail Belkin, and Sathiya Keerthi
16:45 - 17:30 Third Inivited Talk: Yoshua Bengio
Reassuring and Troubling Views on Graph-Based Semi-Supervised Learning
17:30 - 18:00 Open Discussion
|
