• Home
  • Search
  • Algorithmic Concept-Based Explainable Reasoning
  • Cite Icon6
  • https://doi.org/10.1609/aaai.v36i6.20623Copy DOI Icon

Algorithmic Concept-Based Explainable Reasoning

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, such as allowing applications of algorithms when preconditions are not satisfied, or reusing learned models when sufficient training data is not available or can't be generated. Unfortunately, a key hindrance of these approaches is their lack of explainability, since GNNs are black-box models that cannot be interpreted directly. In this work, we address this limitation by applying existing work on concept-based explanations to GNN models. We introduce concept-bottleneck GNNs, which rely on a modification to the GNN readout mechanism. Using three case studies we demonstrate that: (i) our proposed model is capable of accurately learning concepts and extracting propositional formulas based on the learned concepts for each target class; (ii) our concept-based GNN models achieve comparative performance with state-of-the-art models; (iii) we can derive global graph concepts, without explicitly providing any supervision on graph-level concepts.

Similar Papers
  • PDF
  • Research Article
  • Citations23

Prediction of emergency department revisits among child and youth mental health outpatients using deep learning techniques

  • Feb 08, 2024
  • BMC Medical Informatics and Decision Making
  • Simran Saggu +8
  • Research Article
  • Citations1

Enhancing CYP3A4 Inhibition Prediction Using a Hybrid GNN\u2013ML Model with Data Augmentation

  • Feb 02, 2026
  • Pharmaceuticals
  • Somin Woo +4
  • PDF
  • Research Article
  • Citations494

A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions

  • Jan 16, 2024
  • Journal of Big Data
  • Bharti Khemani +3
  • Research Article
  • Citations1

Abstract 1922: Application of an interpretable graph neural network to predict gene expression signatures associated with tertiary lymphoid structures in histopathological images

  • Jun 15, 2022
  • Cancer Research
  • Ciyue Shen +10
  • Conference Article
  • Citations38

Watermarking Graph Neural Networks by Random Graphs

  • Jun 28, 2021
  • Xiangyu Zhao +2
  • Research Article
  • Citations23

Leveraging Persistent Homology Features for Accurate Defect Formation Energy Predictions via Graph Neural Networks.

  • Feb 06, 2025
  • Chemistry of materials : a publication of the American Chemical Society
  • Zhenyao Fang +1
  • PDF
  • Research Article
  • Citations43

Brain age prediction using the graph neural network based on resting-state functional MRI in Alzheimer's disease.

  • Jun 30, 2023
  • Frontiers in neuroscience
  • Jingjing Gao +4
  • Research Article
  • Citations5

Application of an Improved Graph Neural Network for Drug Property Prediction

  • Jan 01, 2024
  • IEEE Access
  • Xiaopu Ma +2
  • PDF
  • Research Article
  • Citations11

Leveraging graph neural networks and neural operator techniques for high-fidelity mesh-based physics simulations

  • Nov 22, 2023
  • APL Machine Learning
  • Zeqing Jin +3
  • Research Article

Attention Mechanism in Line Graph Neural Network for Material Property Prediction

  • Jan 01, 2026
  • Advanced Theory and Simulations
  • Liulei Shao +3
  • Research Article
  • Citations32

A Multi-strategy-based Pre-training Method for Cold-start Recommendation

  • Jan 25, 2023
  • ACM Transactions on Information Systems
  • Bowen Hao +4
  • Research Article
  • Citations1

Robust Lightweight Graph Neural Network Framework for Accelerating Crystal Structure Prediction.

  • Jun 30, 2025
  • Journal of chemical information and modeling
  • Rushikesh Pawar +3
  • Research Article
  • Citations5

Heterogeneous Graph Transformer for Meta-structure Learning with Application in Text Classification

  • May 22, 2023
  • ACM Transactions on the Web
  • Shuhai Wang +4
  • Research Article
  • Citations9

Pre-route timing prediction and optimization with graph neural network models

  • Aug 19, 2024
  • Integration
  • Kyungjoon Chang +1
  • Research Article
  • Citations1

Optimization and Benefit Assessment of Production Supply Chain Networks Using Graph Neural Network Models

  • Jul 15, 2024
  • Journal of Computing and Information Technology
  • Ting Dong +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.