Understanding Post-hoc Explainers: The Case of Anchors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lopardo, Gianluigi, Precioso, Frederic, Garreau, Damien
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908603792752640
author Lopardo, Gianluigi
Precioso, Frederic
Garreau, Damien
author_facet Lopardo, Gianluigi
Precioso, Frederic
Garreau, Damien
contents In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process generating the explanations can be, for a user, as mysterious as the prediction to be explained. Furthermore, interpretability methods frequently lack theoretical guarantees, and their behavior on simple models is frequently unknown. While it is difficult, if not impossible, to ensure that an explainer behaves as expected on a cutting-edge model, we can at least ensure that everything works on simple, already interpretable models. In this paper, we present a theoretical analysis of Anchors (Ribeiro et al., 2018): a popular rule-based interpretability method that highlights a small set of words to explain a text classifier's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results when used with linear text classifiers on top of a TF-IDF vectorization. We believe that our analysis framework can aid in the development of new explainability methods based on solid theoretical foundations.
format Preprint
id arxiv_https___arxiv_org_abs_2303_08806
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Understanding Post-hoc Explainers: The Case of Anchors
Lopardo, Gianluigi
Precioso, Frederic
Garreau, Damien
Machine Learning
Artificial Intelligence
Computation and Language
In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process generating the explanations can be, for a user, as mysterious as the prediction to be explained. Furthermore, interpretability methods frequently lack theoretical guarantees, and their behavior on simple models is frequently unknown. While it is difficult, if not impossible, to ensure that an explainer behaves as expected on a cutting-edge model, we can at least ensure that everything works on simple, already interpretable models. In this paper, we present a theoretical analysis of Anchors (Ribeiro et al., 2018): a popular rule-based interpretability method that highlights a small set of words to explain a text classifier's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results when used with linear text classifiers on top of a TF-IDF vectorization. We believe that our analysis framework can aid in the development of new explainability methods based on solid theoretical foundations.
title Understanding Post-hoc Explainers: The Case of Anchors
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2303.08806