Interpretable Graph Neural Networks for Tabular Data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alkhatib, Amr, Ennadir, Sofiane, Boström, Henrik, Vazirgiannis, Michalis
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913466158153728
author Alkhatib, Amr
Ennadir, Sofiane
Boström, Henrik
Vazirgiannis, Michalis
author_facet Alkhatib, Amr
Ennadir, Sofiane
Boström, Henrik
Vazirgiannis, Michalis
contents Data in tabular format is frequently occurring in real-world applications. Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through representation learning. However, these approaches essentially produce black-box models, in the form of deep neural networks, precluding users from following the logic behind the model predictions. We propose an approach, called IGNNet (Interpretable Graph Neural Network for tabular data), which constrains the learning algorithm to produce an interpretable model, where the model shows how the predictions are exactly computed from the original input features. A large-scale empirical investigation is presented, showing that IGNNet is performing on par with state-of-the-art machine-learning algorithms that target tabular data, including XGBoost, Random Forests, and TabNet. At the same time, the results show that the explanations obtained from IGNNet are aligned with the true Shapley values of the features without incurring any additional computational overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2308_08945
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Interpretable Graph Neural Networks for Tabular Data
Alkhatib, Amr
Ennadir, Sofiane
Boström, Henrik
Vazirgiannis, Michalis
Machine Learning
Artificial Intelligence
Data in tabular format is frequently occurring in real-world applications. Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through representation learning. However, these approaches essentially produce black-box models, in the form of deep neural networks, precluding users from following the logic behind the model predictions. We propose an approach, called IGNNet (Interpretable Graph Neural Network for tabular data), which constrains the learning algorithm to produce an interpretable model, where the model shows how the predictions are exactly computed from the original input features. A large-scale empirical investigation is presented, showing that IGNNet is performing on par with state-of-the-art machine-learning algorithms that target tabular data, including XGBoost, Random Forests, and TabNet. At the same time, the results show that the explanations obtained from IGNNet are aligned with the true Shapley values of the features without incurring any additional computational overhead.
title Interpretable Graph Neural Networks for Tabular Data
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2308.08945