ICML 2015poster61 citations
An Aligned Subtree Kernel for Weighted Graphs
Lu Bai, Luca Rossi, Zhihong Zhang, Edwin Hancock
Abstract
In this paper, we develop a new entropic matching kernel for weighted graphs by aligning depth-based representations. We demonstrate that this kernel can be seen as an \textbfaligned subtree kernel that incorporates explicit subtree correspondences, and thus addresses the drawback of neglecting the relative locations between substructures that arises in the R-convolution kernels. Experiments on standard datasets demonstrate that our kernel can easily outperform state-of-the-art graph kernels in terms of classification accuracy.
BibTeX
@InProceedings{pmlr-v37-bai15,
title = {An Aligned Subtree Kernel for Weighted Graphs},
author = {Bai, Lu and Rossi, Luca and Zhang, Zhihong and Hancock, Edwin},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning},
pages = {30--39},
year = {2015},
editor = {Bach, Francis and Blei, David},
volume = {37},
series = {Proceedings of Machine Learning Research},
address = {Lille, France},
month = {07--09 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v37/bai15.pdf},
url = {https://proceedings.mlr.press/v37/bai15.html},
abstract = {In this paper, we develop a new entropic matching kernel for weighted graphs by aligning depth-based representations. We demonstrate that this kernel can be seen as an \textbfaligned subtree kernel that incorporates explicit subtree correspondences, and thus addresses the drawback of neglecting the relative locations between substructures that arises in the R-convolution kernels. Experiments on standard datasets demonstrate that our kernel can easily outperform state-of-the-art graph kernels in terms of classification accuracy.}
}