Design Requirements for Human-Centered Graph Neural Network Explanations

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Habibi, Pantea, Baghershahi, Peyman, Medya, Sourav, Chattopadhyay, Debaleena
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911874319122432
author Habibi, Pantea
Baghershahi, Peyman
Medya, Sourav
Chattopadhyay, Debaleena
author_facet Habibi, Pantea
Baghershahi, Peyman
Medya, Sourav
Chattopadhyay, Debaleena
contents Graph neural networks (GNNs) are powerful graph-based machine-learning models that are popular in various domains, e.g., social media, transportation, and drug discovery. However, owing to complex data representations, GNNs do not easily allow for human-intelligible explanations of their predictions, which can decrease trust in them as well as deter any collaboration opportunities between the AI expert and non-technical, domain expert. Here, we first discuss the two papers that aim to provide GNN explanations to domain experts in an accessible manner and then establish a set of design requirements for human-centered GNN explanations. Finally, we offer two example prototypes to demonstrate some of those proposed requirements.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06917
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Design Requirements for Human-Centered Graph Neural Network Explanations
Habibi, Pantea
Baghershahi, Peyman
Medya, Sourav
Chattopadhyay, Debaleena
Machine Learning
Human-Computer Interaction
Graph neural networks (GNNs) are powerful graph-based machine-learning models that are popular in various domains, e.g., social media, transportation, and drug discovery. However, owing to complex data representations, GNNs do not easily allow for human-intelligible explanations of their predictions, which can decrease trust in them as well as deter any collaboration opportunities between the AI expert and non-technical, domain expert. Here, we first discuss the two papers that aim to provide GNN explanations to domain experts in an accessible manner and then establish a set of design requirements for human-centered GNN explanations. Finally, we offer two example prototypes to demonstrate some of those proposed requirements.
title Design Requirements for Human-Centered Graph Neural Network Explanations
topic Machine Learning
Human-Computer Interaction
url https://arxiv.org/abs/2405.06917