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

Concept-based explanations have emerged as a popular way of extractinghuman-interpretable representations from deep discriminative models. At thesame time, the disentanglement learning literature has focused on extractingsimilar representations in an unsupervised or weakly-supervised way, using deepgenerative models. Despite the overlapping goals and potential synergies, toour knowledge, there has not yet been a systematic comparison of thelimitations and trade-offs between concept-based explanations anddisentanglement approaches. In this paper, we give an overview of these fields,comparing and contrasting their properties and behaviours on a diverse set oftasks, and highlighting their potential strengths and limitations. Inparticular, we demonstrate that state-of-the-art approaches from both classescan be data inefficient, sensitive to the specific nature of theclassification/regression task, or sensitive to the employed conceptrepresentation.

Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches