Generating Contrastive Explanations with Monotonic Attribute Functions

05/29/2019
by   Ronny Luss, et al.
9

Explaining decisions of deep neural networks is a hot research topic with applications in medical imaging, video surveillance, and self driving cars. Many methods have been proposed in literature to explain these decisions by identifying relevance of different pixels. In this paper, we propose a method that can generate contrastive explanations for such data where we not only highlight aspects that are in themselves sufficient to justify the classification by the deep model, but also new aspects which if added will change the classification. One of our key contributions is how we define "addition" for such rich data in a formal yet humanly interpretable way that leads to meaningful results. This was one of the open questions laid out in Dhurandhar et.al. (2018) [5], which proposed a general framework for creating (local) contrastive explanations for deep models. We showcase the efficacy of our approach on CelebA and Fashion-MNIST in creating intuitive explanations that are also quantitatively superior compared with other state-of-the-art interpretability methods.

READ FULL TEXT

page 7

page 19

page 20

research
12/27/2020

Explaining NLP Models via Minimal Contrastive Editing (MiCE)

Humans give contrastive explanations that explain why an observed event ...
research
05/31/2019

Model Agnostic Contrastive Explanations for Structured Data

Recently, a method [7] was proposed to generate contrastive explanations...
research
09/16/2021

Let the CAT out of the bag: Contrastive Attributed explanations for Text

Contrastive explanations for understanding the behavior of black box mod...
research
03/02/2021

Contrastive Explanations for Model Interpretability

Contrastive explanations clarify why an event occurred in contrast to an...
research
12/05/2018

Understanding Individual Decisions of CNNs via Contrastive Backpropagation

A number of backpropagation-based approaches such as DeConvNets, vanilla...
research
08/01/2020

Contrastive Explanations in Neural Networks

Visual explanations are logical arguments based on visual features that ...
research
06/15/2019

LioNets: Local Interpretation of Neural Networks through Penultimate Layer Decoding

Technological breakthroughs on smart homes, self-driving cars, health ca...

Please sign up or login with your details

Forgot password? Click here to reset