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.

References in corpus (6)

• Complex Embeddings for Simple Link Prediction
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• KG-BERT: BERT for Knowledge Graph Completion
• Quaternion Knowledge Graph Embeddings
• Relational Graph Attention Networks

Cited by in corpus (2)

• A Review of Knowledge Graph Completion
• Relational Graph Convolutional Networks: A Closer Look