Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Generating Explanations for Conceptual Validation of Graph Neural Networks : An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs

Publication

Generating Explanations for Conceptual Validation of Graph Neural Networks : An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs

Finzel, Bettina; Saranti, Anna; Angerschmid, Alessa; u. a. (2023): Generating Explanations for Conceptual Validation of Graph Neural Networks : An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs, in: Bamberg: Otto-Friedrich-Universität, S. 271–285.

Details

Faculty/Chair
Faculty/Professorship
Author
Saranti, Anna
Angerschmid, Alessa
Tafler, David
Pfeifer, Bastian
Holzinger, Andreas
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2023
Source/Other editions
Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI, 36 (2022), 3-4, S. 271–285. - ISSN: 0933-1875, 1610-1987
Year of first publication
2022
Language
English
Licence
URN
Abstract

Graph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain’s and user’s perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs, is an essential forward-looking step to perform powerful and validatable relational concept learning. In this contribution, we introduce a benchmark for the conceptual validation of GNN classification outputs. It consists of the symbolic representations of symmetric and non-symmetric figures that are taken from a well-known Kandinsky Pattern data set. We further provide a novel validation framework that can be used to generate comprehensible explanations with ILP on top of the relevance output of GNN explainers and human-expected relevance for concepts learned by GNNs. Our experiments conducted on our benchmark data set demonstrate that it is possible to extract symbolic concepts from the most relevant explanations that are representative of what a GNN has learned. Our findings open up a variety of avenues for future research on validatable explanations for GNNs.

GND Keywords
Neuronales Netz
Wissensgraph
Explainable Artificial Intelligence
Induktive logische Programmierung
Keywords
Graph neural networks (GNN)
Explainable AI (xAI)
Inductive logic programming (ILP)
Symbolic AI
Kandinsky pattern (KP)
DDC Classification
004 Computer science
RVK Classification
ST 304
Type
Article
URI
Activation date
2024-03-11

Permalink: https://fis.uni-bamberg.de/handle/uniba/91640 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.