Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs
Abstract
Recently, explanation methods have been proposed to evaluate the predictions of Graph Neural Networks on the task of link prediction. Evaluating explanation quality is difficult without ground truth explanations. This thesis is focused on providing a method, including datasets and scoring metrics, to quantitatively evaluate explanation methods on link prediction on Knowledge Graphs.
Cite
Text
Halliwell. "Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21577Markdown
[Halliwell. "Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/halliwell2022aaai-evaluating/) doi:10.1609/AAAI.V36I11.21577BibTeX
@inproceedings{halliwell2022aaai-evaluating,
title = {{Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs}},
author = {Halliwell, Nicholas},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {12880-12881},
doi = {10.1609/AAAI.V36I11.21577},
url = {https://mlanthology.org/aaai/2022/halliwell2022aaai-evaluating/}
}