Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs
Keywords:Link Prediction, Explainable AI, Knowledge Graphs, Graph Neural Networks, Explanation Evaluation
AbstractRecently, 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.
How to Cite
Halliwell, N. (2022). Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12880-12881. https://doi.org/10.1609/aaai.v36i11.21577
The Twenty - Seventh AAAI / SIGAI Doctoral Consortium