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

Despite the recent development in the topic of explainable AI/ML for imageand text data, the majority of current solutions are not suitable to explainthe prediction of neural network models when the datasets are tabular and theirfeatures are in high-dimensional vectorized formats. To mitigate thislimitation, therefore, we borrow two notable ideas (i.e., "explanation byintervention" from causality and "explanation are contrastive" from philosophy)and propose a novel solution, named as GRACE, that better explains neuralnetwork models' predictions for tabular datasets. In particular, given amodel's prediction as label X, GRACE intervenes and generates aminimally-modified contrastive sample to be classified as Y, with an intuitivetextual explanation, answering the question of "Why X rather than Y?" We carryout comprehensive experiments using eleven public datasets of different scalesand domains (e.g., # of features ranges from 5 to 216) and compare GRACE withcompeting baselines on different measures: fidelity, conciseness, info-gain,and influence. The user-studies show that our generated explanation is not onlymore intuitive and easy-to-understand but also facilitates end-users to make asmuch as 60% more accurate post-explanation decisions than that of Lime.

GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction