An Aligned Subtree Kernel for Weighted Graphs

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 \textbf{aligned} 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.

Cite

Text

Bai et al. "An Aligned Subtree Kernel for Weighted Graphs." International Conference on Machine Learning, 2015.

Markdown

[Bai et al. "An Aligned Subtree Kernel for Weighted Graphs." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/bai2015icml-aligned/)

BibTeX

@inproceedings{bai2015icml-aligned,
  title     = {{An Aligned Subtree Kernel for Weighted Graphs}},
  author    = {Bai, Lu and Rossi, Luca and Zhang, Zhihong and Hancock, Edwin},
  booktitle = {International Conference on Machine Learning},
  year      = {2015},
  pages     = {30-39},
  volume    = {37},
  url       = {https://mlanthology.org/icml/2015/bai2015icml-aligned/}
}