Knowledge Graph Reasoning with Relational Digraph
About
Reasoning on the knowledge graph (KG) aims to infer new facts from existing ones. Methods based on the relational path have shown strong, interpretable, and transferable reasoning ability. However, paths are naturally limited in capturing local evidence in graphs. In this paper, we introduce a novel relational structure, i.e., relational directed graph (r-digraph), which is composed of overlapped relational paths, to capture the KG's local evidence. Since the r- digraphs are more complex than paths, how to efficiently construct and effectively learn from them are challenging. Directly encoding the r-digraphs cannot scale well and capturing query-dependent information is hard in r-digraphs. We propose a variant of graph neural network, i.e., RED-GNN, to address the above challenges. Specifically, RED-GNN makes use of dynamic programming to recursively encodes multiple r-digraphs with shared edges, and utilizes a query-dependent attention mechanism to select the strongly correlated edges. We demonstrate that RED-GNN is not only efficient but also can achieve significant performance gains in both inductive and transductive reasoning tasks over existing methods. Besides, the learned attention weights in RED-GNN can exhibit interpretable evidence for KG reasoning.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Knowledge Graph Completion | UMLS | Hits@100.99 | 29 | |
| Knowledge Graph Completion | WN18RR standard (transductive) | MRR53.8 | 14 | |
| Knowledge Graph Completion | FB15k-237 standard (transductive) | MRR0.376 | 14 | |
| Knowledge Graph Completion | NELL-995 | MRR0.543 | 8 | |
| Knowledge Graph Completion | Family | MRR99.2 | 7 | |
| Inductive Knowledge Graph Completion | NELL-995 v4 | MRR31.7 | 7 | |
| Knowledge Graph Completion | WN18RR-ind v1 | Hits@165.3 | 7 | |
| Inductive Knowledge Graph Completion | WN18RR V1 | MRR0.7 | 7 | |
| Inductive Knowledge Graph Completion | WN18RR V2 | MRR0.689 | 7 | |
| Inductive Knowledge Graph Completion | WN18RR V3 | MRR42.9 | 7 |