GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
This addresses the need for accurate and explainable graph classification, though it appears incremental by integrating existing explanation techniques.
The authors tackled graph classification by introducing GDLNN, which combines a domain-specific programming language (GDL) with neural networks to generate interpretable representations, achieving high accuracy and outperforming methods like GNNs on benchmark datasets.
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.