r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
This addresses the problem of modeling complex multi-relational graphs like knowledge graphs for researchers and practitioners in graph learning, representing an incremental improvement over existing GAT methods.
The paper tackled the limitation of Graph Attention Networks (GAT) in handling multi-relational graphs by proposing r-GAT, which learns multi-channel entity representations and uses a query-aware attention mechanism, resulting in effective modeling as shown in link prediction and entity classification experiments.
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.