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

The minimal feature removal problem in the post-hoc explanation area aims toidentify the minimal feature set (MFS). Prior studies using the greedyalgorithm to calculate the minimal feature set lack the exploration of featureinteractions under a monotonic assumption which cannot be satisfied in generalscenarios. In order to address the above limitations, we propose a CooperativeIntegrated Dynamic Refining method (CIDR) to efficiently discover minimalfeature sets. Specifically, we design Cooperative Integrated Gradients (CIG) todetect interactions between features. By incorporating CIG and characteristicsof the minimal feature set, we transform the minimal feature removal probleminto a knapsack problem. Additionally, we devise an auxiliary Minimal FeatureRefinement algorithm to determine the minimal feature set from numerouscandidate sets. To the best of our knowledge, our work is the first to addressthe minimal feature removal problem in the field of natural languageprocessing. Extensive experiments demonstrate that CIDR is capable of tracingrepresentative minimal feature sets with improved interpretability acrossvarious models and datasets.

CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem