Advanced graph kernels: The Weisfeiler-Lehman Kernel

Karsten Borgwardt, Nino ShervashidzeMPG.PuRe 2010

Abstract

Key concept: Move learning task to feature space H. Naive explicit approach:Map objects x and x via mapping to H.Measure their similarity in H as (x), (x ) .Kernel Trick: Compute inner product in H as kernel in input space k(x, x ) = (x), (x ) .
BibTeX
@inproceedings{borgwardt2010advanced,
  author = {Karsten Borgwardt and Nino Shervashidze},
  title = {{Advanced graph kernels: The Weisfeiler-Lehman Kernel}},
  booktitle = {MPG.PuRe},
  year = {2010},
}

Loading related content...

Figure