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/

Zendy Plus

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

Zendy Tools

Zendy Open

The benefit of locality is one of the major premises of LIME, one of the mostprominent methods to explain black-box machine learning models. This emphasisrelies on the postulate that the more locally we look at the vicinity of aninstance, the simpler the black-box model becomes, and the more accurately wecan mimic it with a linear surrogate. As logical as this seems, our findingssuggest that, with the current design of LIME, the surrogate model maydegenerate when the explanation is too local, namely, when the bandwidthparameter $\sigma$ tends to zero. Based on this observation, the contributionof this paper is twofold. Firstly, we study the impact of both the bandwidthand the training vicinity on the fidelity and semantics of LIME explanations.Secondly, and based on our findings, we propose \slime, an extension of LIMEthat reconciles fidelity and locality.

s-LIME: Reconciling Locality and Fidelity in Linear Explanations