Efficient Explanations from Empirical Explainers

03/29/2021
by   Robert Schwarzenberg, et al.
0

Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers. To this end, we propose the task of feature attribution modelling that we address with Empirical Explainers. Empirical Explainers learn from data to predict the attribution maps of expensive explainers. We train and test Empirical Explainers in the language domain and find that they model their expensive counterparts well, at a fraction of the cost. They could thus mitigate the computational burden of neural explanations significantly, in applications that tolerate an approximation error.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

09/28/2021

Who Explains the Explanation? Quantitatively Assessing Feature Attribution Methods

AI explainability seeks to increase the transparency of models, making t...
04/09/2021

An Empirical Comparison of Instance Attribution Methods for NLP

Widespread adoption of deep models has motivated a pressing need for app...
08/31/2021

Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools

In the language domain, as in other domains, neural explainability takes...
09/21/2021

Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation

Feedback can help crowdworkers to improve their ideations. However, curr...
02/28/2022

An Empirical Study on Explanations in Out-of-Domain Settings

Recent work in Natural Language Processing has focused on developing app...
09/18/2020

On the Tractability of SHAP Explanations

SHAP explanations are a popular feature-attribution mechanism for explai...
12/06/2021

What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods

A multitude of explainability methods and theoretical evaluation scores ...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.