Diffusion Kernels on Graphs and Other Discrete Input Spaces
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Transductive Inference for Text Classification using Support Vector Machines
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Learning the Kernel Matrix with Semi-Definite Programming
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
STOC '04 Proceedings of the thirty-sixth annual ACM symposium on Theory of computing
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection
The Journal of Machine Learning Research
Learning the Kernel with Hyperkernels
The Journal of Machine Learning Research
Beyond the point cloud: from transductive to semi-supervised learning
ICML '05 Proceedings of the 22nd international conference on Machine learning
Fast protein classification with multiple networks
Bioinformatics
Statistical Comparisons of Classifiers over Multiple Data Sets
The Journal of Machine Learning Research
Large Scale Multiple Kernel Learning
The Journal of Machine Learning Research
Graph sharpening plus graph integration
Bioinformatics
Protein functional class prediction with a combined graph
Expert Systems with Applications: An International Journal
Graph based semi-supervised learning with sharper edges
ECML'06 Proceedings of the 17th European conference on Machine Learning
Stock price prediction based on a complex interrelation network of economic factors
Engineering Applications of Artificial Intelligence
Prediction of movement direction in crude oil prices based on semi-supervised learning
Decision Support Systems
Robust predictive model for evaluating breast cancer survivability
Engineering Applications of Artificial Intelligence
Sharpened graph ensemble for semi-supervised learning
Intelligent Data Analysis
Hi-index | 12.05 |
In many graph-based semi-supervised learning algorithms, edge weights are assumed to be fixed and determined by the data points' (often symmetric) relationships in input space, without considering directionality. However, relationships may be more informative in one direction (e.g. from labelled to unlabelled) than in the reverse direction, and some relationships (e.g. strong weights between oppositely labelled points) are unhelpful in either direction. Undesirable edges may reduce the amount of influence an informative point can propagate to its neighbours - the point and its outgoing edges have been ''blunted.'' We present an approach to ''sharpening'' in which weights are adjusted to meet an optimization criterion wherever they are directed towards labelled points. This principle can be applied to a wide variety of algorithms. In this paper, we present one solution satisfying the principle, in order to show that it can improve performance on a number of publicly available bench-mark data sets. When tested on a real-world problem, protein function classification with four vastly different molecular similarity graphs, sharpening improved ROC scores by 16% on average, at negligible computational cost.