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

In addition to high accuracy, robustness is becoming increasingly importantfor machine learning models in various applications. Recently, much researchhas been devoted to improving the model robustness by training with noiseperturbations. Most existing studies assume a fixed perturbation level for alltraining examples, which however hardly holds in real tasks. In fact, excessiveperturbations may destroy the discriminative content of an example, whiledeficient perturbations may fail to provide helpful information for improvingthe robustness. Motivated by this observation, we propose to adaptively adjustthe perturbation levels for each example in the training process. Specifically,a novel active learning framework is proposed to allow the model tointeractively query the correct perturbation level from human experts. Bydesigning a cost-effective sampling strategy along with a new query type, therobustness can be significantly improved with a few queries. Both theoreticalanalysis and experimental studies validate the effectiveness of the proposedapproach.

Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries