r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
Abstract
Graph Attention Network (GAT) focuses on modelling simple undirected and single relational graph data only. This limits its ability to deal with more general and complex multi-relational graphs that contain entities with directed links of different labels (e.g., knowledge graphs). Therefore, directly applying GAT on multi-relational graphs leads to sub-optimal solutions. To tackle this issue, we propose r-GAT, a relational graph attention network to learn multi-channel entity representations. Specifically, each channel corresponds to a latent semantic aspect of an entity. This enables us to aggregate neighborhood information for the current aspect using relation features. We further propose a query-aware attention mechanism for subsequent tasks to select useful aspects. Extensive experiments on link prediction and entity classification tasks show that our r-GAT can model multi-relational graphs effectively. Also, we show the interpretability of our approach by case study.
Cite
@article{arxiv.2109.05922,
title = {r-GAT: Relational Graph Attention Network for Multi-Relational Graphs},
author = {Meiqi Chen and Yuan Zhang and Xiaoyu Kou and Yuntao Li and Yan Zhang},
journal= {arXiv preprint arXiv:2109.05922},
year = {2021}
}