Skip to Main content Skip to Navigation
Poster communications

A Simplified Benchmark for Non-ambiguous Explanations of Knowledge Graph Link Prediction using Relational Graph Convolutional Networks

Nicholas Halliwell 1 Fabien Gandon 1 Freddy Lecue 2, 1
1 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : Relational Graph Convolutional Networks (RGCNs) identify relationships within a Knowledge Graph to learn real-valued embeddings for each node and edge. Recently, researchers have proposed explanation methods to interpret the predictions of these black-box models. However, comparisons across explanation methods is difficult without a common dataset and standard evaluation metrics to evaluate the explanations. In this paper, we propose a method, including two datasets (Royalty-20k and Royalty-30k), to benchmark explanation methods on the task of explainable link prediction using Graph Neural Networks. We report the results of state-of-the-art explanation methods for RGCNs.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03339562
Contributor : Nicholas Halliwell Connect in order to contact the contributor
Submitted on : Thursday, September 9, 2021 - 3:19:08 PM
Last modification on : Wednesday, November 3, 2021 - 3:48:18 AM

File

paper326.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03339562, version 1

Citation

Nicholas Halliwell, Fabien Gandon, Freddy Lecue. A Simplified Benchmark for Non-ambiguous Explanations of Knowledge Graph Link Prediction using Relational Graph Convolutional Networks. International Semantic Web Conference, Oct 2021, Troy, United States. ⟨hal-03339562v1⟩

Share

Metrics

Record views

62

Files downloads

61