Transductive Inference for Text Classification using Support Vector Machines
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
A Generalized Representer Theorem
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Convex Optimization
A continuation method for semi-supervised SVMs
ICML '06 Proceedings of the 23rd international conference on Machine learning
Trading convexity for scalability
ICML '06 Proceedings of the 23rd international conference on Machine learning
Deterministic annealing for semi-supervised kernel machines
ICML '06 Proceedings of the 23rd international conference on Machine learning
Support Vector Machines
Fast evolutionary maximum margin clustering
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Prototype vector machine for large scale semi-supervised learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Introduction to Semi-Supervised Learning
Introduction to Semi-Supervised Learning
Semi-Supervised Learning
Semisupervised Least Squares Support Vector Machine
IEEE Transactions on Neural Networks
On ensemble classifiers for nonintrusive appliance load monitoring
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part I
Hi-index | 0.00 |
In real-world machine learning scenarios, labeled data is often rare while unlabeled data can be obtained easily. Semi-supervised approaches aim at improving the prediction performance by taking both the labeled as well as the unlabeled part of the data into account. In particular, semi-supervised support vector machines favor decision hyperplanes which lie in a "low-density area" induced by the unlabeled patterns (while still considering the labeled part of the data). The associated optimization problem, however, is of combinatorial nature and, hence, difficult to solve. In this work, we present an efficient implementation of a simple local search strategy that is based on matrix updates of the intermediate candidate solutions. Our experiments on both artificial and real-world data sets indicate that the approach can successfully incorporate unlabeled data in an efficient manner.