Saved in:
Bibliographic Details
Main Authors: Jeon, Minseok, Park, Seunghyun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911187553222656
author Jeon, Minseok
Park, Seunghyun
author_facet Jeon, Minseok
Park, Seunghyun
contents We present GDLNN, a new graph machine learning architecture, for graph classification tasks. GDLNN combines a domain-specific programming language, called GDL, with neural networks. The main strength of GDLNN lies in its GDL layer, which generates expressive and interpretable graph representations. Since the graph representation is interpretable, existing model explanation techniques can be directly applied to explain GDLNN's predictions. Our evaluation shows that the GDL-based representation achieves high accuracy on most graph classification benchmark datasets, outperforming dominant graph learning methods such as GNNs. Applying an existing model explanation technique also yields high-quality explanations of GDLNN's predictions. Furthermore, the cost of GDLNN is low when the explanation cost is included.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
Jeon, Minseok
Park, Seunghyun
Machine Learning
Computation and Language
We present GDLNN, a new graph machine learning architecture, for graph classification tasks. GDLNN combines a domain-specific programming language, called GDL, with neural networks. The main strength of GDLNN lies in its GDL layer, which generates expressive and interpretable graph representations. Since the graph representation is interpretable, existing model explanation techniques can be directly applied to explain GDLNN's predictions. Our evaluation shows that the GDL-based representation achieves high accuracy on most graph classification benchmark datasets, outperforming dominant graph learning methods such as GNNs. Applying an existing model explanation technique also yields high-quality explanations of GDLNN's predictions. Furthermore, the cost of GDLNN is low when the explanation cost is included.
title GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2510.00374