Verifying Relational Explanations: A Probabilistic Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Magar, Abisha Thapa, Shakya, Anup, Sarkhel, Somdeb, Venugopal, Deepak
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913186755641344
author Magar, Abisha Thapa
Shakya, Anup
Sarkhel, Somdeb
Venugopal, Deepak
author_facet Magar, Abisha Thapa
Shakya, Anup
Sarkhel, Somdeb
Venugopal, Deepak
contents Explanations on relational data are hard to verify since the explanation structures are more complex (e.g. graphs). To verify interpretable explanations (e.g. explanations of predictions made in images, text, etc.), typically human subjects are used since it does not necessarily require a lot of expertise. However, to verify the quality of a relational explanation requires expertise and is hard to scale-up. GNNExplainer is arguably one of the most popular explanation methods for Graph Neural Networks. In this paper, we develop an approach where we assess the uncertainty in explanations generated by GNNExplainer. Specifically, we ask the explainer to generate explanations for several counterfactual examples. We generate these examples as symmetric approximations of the relational structure in the original data. From these explanations, we learn a factor graph model to quantify uncertainty in an explanation. Our results on several datasets show that our approach can help verify explanations from GNNExplainer by reliably estimating the uncertainty of a relation specified in the explanation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02703
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Verifying Relational Explanations: A Probabilistic Approach
Magar, Abisha Thapa
Shakya, Anup
Sarkhel, Somdeb
Venugopal, Deepak
Artificial Intelligence
Explanations on relational data are hard to verify since the explanation structures are more complex (e.g. graphs). To verify interpretable explanations (e.g. explanations of predictions made in images, text, etc.), typically human subjects are used since it does not necessarily require a lot of expertise. However, to verify the quality of a relational explanation requires expertise and is hard to scale-up. GNNExplainer is arguably one of the most popular explanation methods for Graph Neural Networks. In this paper, we develop an approach where we assess the uncertainty in explanations generated by GNNExplainer. Specifically, we ask the explainer to generate explanations for several counterfactual examples. We generate these examples as symmetric approximations of the relational structure in the original data. From these explanations, we learn a factor graph model to quantify uncertainty in an explanation. Our results on several datasets show that our approach can help verify explanations from GNNExplainer by reliably estimating the uncertainty of a relation specified in the explanation.
title Verifying Relational Explanations: A Probabilistic Approach
topic Artificial Intelligence
url https://arxiv.org/abs/2401.02703