CUED Publications database

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

Kazhdan, D and Dimanov, B and Terre, HA and Jamnik, M and Liò, P and Weller, A Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches. (Unpublished)

Full text not available from this repository.

Abstract

Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement learning literature has focused on extracting similar representations in an unsupervised or weakly-supervised way, using deep generative models. Despite the overlapping goals and potential synergies, to our knowledge, there has not yet been a systematic comparison of the limitations and trade-offs between concept-based explanations and disentanglement approaches. In this paper, we give an overview of these fields, comparing and contrasting their properties and behaviours on a diverse set of tasks, and highlighting their potential strengths and limitations. In particular, we demonstrate that state-of-the-art approaches from both classes can be data inefficient, sensitive to the specific nature of the classification/regression task, or sensitive to the employed concept representation.

Item Type: Article
Uncontrolled Keywords: cs.LG cs.LG cs.AI
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 16 Apr 2021 20:08
Last Modified: 01 Jul 2021 09:12
DOI: