Probabilistic Sufficient Explanations

05/21/2021
by   Eric Wang, et al.
0

Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed. In this paper, we introduce probabilistic sufficient explanations, which formulate explaining an instance of classification as choosing the "simplest" subset of features such that only observing those features is "sufficient" to explain the classification. That is, sufficient to give us strong probabilistic guarantees that the model will behave similarly when all features are observed under the data distribution. In addition, we leverage tractable probabilistic reasoning tools such as probabilistic circuits and expected predictions to design a scalable algorithm for finding the desired explanations while keeping the guarantees intact. Our experiments demonstrate the effectiveness of our algorithm in finding sufficient explanations, and showcase its advantages compared to Anchors and logical explanations.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

page 10

11/08/2021

Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models

To explain the decision of any model, we extend the notion of probabilis...
12/21/2020

On Relating 'Why?' and 'Why Not?' Explanations

Explanations of Machine Learning (ML) models often address a 'Why?' ques...
06/29/2021

Semantic Reasoning from Model-Agnostic Explanations

With the wide adoption of black-box models, instance-based post hoc expl...
09/23/2020

The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets

For neural models to garner widespread public trust and ensure fairness,...
07/02/2018

Logical Explanations for Deep Relational Machines Using Relevance Information

Our interest in this paper is in the construction of symbolic explanatio...
11/01/2021

Provably efficient, succinct, and precise explanations

We consider the problem of explaining the predictions of an arbitrary bl...
09/13/2021

Towards Better Model Understanding with Path-Sufficient Explanations

Feature based local attribution methods are amongst the most prevalent i...
This week in AI

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