A polynomial time computable metric between point sets
Acta Informatica
Limitations of learning via embeddings in euclidean half spaces
The Journal of Machine Learning Research
A survey of kernels for structured data
ACM SIGKDD Explorations Newsletter
Kernel Methods for Pattern Analysis
Kernel Methods for Pattern Analysis
Learning the Kernel Matrix with Semidefinite Programming
The Journal of Machine Learning Research
Cyclic pattern kernels for predictive graph mining
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Kernels and Distances for Structured Data
Machine Learning
Protein function prediction via graph kernels
Bioinformatics
Weighted decomposition kernels
ICML '05 Proceedings of the 22nd international conference on Machine learning
Shortest-Path Kernels on Graphs
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
2005 Speical Issue: Graph kernels for chemical informatics
Neural Networks - Special issue on neural networks and kernel methods for structured domains
Distances and (Indefinite) Kernels for Sets of Objects
ICDM '06 Proceedings of the Sixth International Conference on Data Mining
The Dissimilarity Representation for Pattern Recognition: Foundations And Applications (Machine Perception and Artificial Intelligence)
| Hi-index | 0.00 |
Several kernels over labelled graphs have been proposed in the literature so far Most of them are based on the Cross Product (CP) Kernel applied on decompositions of graphs into sub-graphs of specific types This approach has two main limitations: (i) it is difficult to choose a-priori the appropriate type of sub-graphs for a given problem and (ii) all the sub-graphs of a decomposition participate in the computation of the CP kernel even though many of them might be poorly correlated with the class variable To tackle these problems we propose a class of graph kernels constructed on the proximity space induced by the graph distances These graph distances address the aforementioned limitations by learning combinations of different types of graph decompositions and by flexible matching the elements of the decompositions Experiments performed on a number of graph classification problems demonstrate the effectiveness of the proposed approach.