Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation

09/09/2021
by   Thien Q. Tran, et al.
0

We aim to explain a black-box classifier with the form: `data X is classified as class Y because X has A, B and does not have C' in which A, B, and C are high-level concepts. The challenge is that we have to discover in an unsupervised manner a set of concepts, i.e., A, B and C, that is useful for the explaining the classifier. We first introduce a structural generative model that is suitable to express and discover such concepts. We then propose a learning process that simultaneously learns the data distribution and encourages certain concepts to have a large causal influence on the classifier output. Our method also allows easy integration of user's prior knowledge to induce high interpretability of concepts. Using multiple datasets, we demonstrate that our method can discover useful binary concepts for explanation.

READ FULL TEXT

page 2

page 7

page 8

page 16

page 17

page 18

research
06/24/2020

Generative causal explanations of black-box classifiers

We develop a method for generating causal post-hoc explanations of black...
research
07/10/2021

Using Causal Analysis for Conceptual Deep Learning Explanation

Model explainability is essential for the creation of trustworthy Machin...
research
06/01/2022

Discovering the Hidden Vocabulary of DALLE-2

We discover that DALLE-2 seems to have a hidden vocabulary that can be u...
research
05/31/2021

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals

Explaining deep learning model inferences is a promising venue for scien...
research
06/03/2020

Explaining The Behavior Of Black-Box Prediction Algorithms With Causal Learning

We propose to explain the behavior of black-box prediction methods (e.g....
research
05/23/2017

Explaining Transition Systems through Program Induction

Explaining and reasoning about processes which underlie observed black-b...
research
08/16/2020

Towards Faithful and Meaningful Interpretable Representations

Interpretable representations are the backbone of many black-box explain...

Please sign up or login with your details

Forgot password? Click here to reset