Corpus ID: 231984658

Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels

@inproceedings{Ru2020InterpretableNA,
  title={Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels},
  author={Binxin Ru and Xingchen Wan and Xiaowen Dong and Michael Osborne},
  year={2020}
}
  • Binxin Ru, Xingchen Wan, +1 author Michael Osborne
  • Published 2020
  • Computer Science, Mathematics
  • Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or how we should modify the architecture if we want further improvements. We propose a Bayesian optimisation (BO) approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate. Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the… CONTINUE READING
    1 Citations