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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neural Architecture Search (NAS) has shown great potentials in finding betterneural network designs. Sample-based NAS is the most reliable approach whichaims at exploring the search space and evaluating the most promisingarchitectures. However, it is computationally very costly. As a remedy, theone-shot approach has emerged as a popular technique for accelerating NAS usingweight-sharing. However, due to the weight-sharing of vastly differentnetworks, the one-shot approach is less reliable than the sample-basedapproach. In this work, we propose BONAS (Bayesian Optimized NeuralArchitecture Search), a sample-based NAS framework which is accelerated usingweight-sharing to evaluate multiple related architectures simultaneously.Specifically, we apply Graph Convolutional Network predictor as a surrogatemodel for Bayesian Optimization to select multiple related candidate models ineach iteration. We then apply weight-sharing to train multiple candidate modelssimultaneously. This approach not only accelerates the traditional sample-basedapproach significantly, but also keeps its reliability. This is becauseweight-sharing among related architectures are more reliable than those in theone-shot approach. Extensive experiments are conducted to verify theeffectiveness of our method over many competing algorithms.

Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS