English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Current neural architecture search (NAS) strategies focus only on finding asingle, good, architecture. They offer little insight into why a specificnetwork is performing well, or how we should modify the architecture if we wantfurther improvements. We propose a Bayesian optimisation (BO) approach for NASthat combines the Weisfeiler-Lehman graph kernel with a Gaussian processsurrogate. Our method optimises the architecture in a highly data-efficientmanner: it is capable of capturing the topological structures of thearchitectures and is scalable to large graphs, thus making the high-dimensionaland graph-like search spaces amenable to BO. More importantly, our methodaffords interpretability by discovering useful network features and theircorresponding impact on the network performance. Indeed, we demonstrateempirically that our surrogate model is capable of identifying useful motifswhich can guide the generation of new architectures. We finally show that ourmethod outperforms existing NAS approaches to achieve the state of the art onboth closed- and open-domain search spaces.

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