Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Yongqi Zhang, Quanming Yao• 2021

Related benchmarks

TaskDatasetResultRank
Knowledge Graph CompletionUMLS
Hits@100.99
29
Knowledge Graph CompletionWN18RR standard (transductive)
MRR53.8
14
Knowledge Graph CompletionFB15k-237 standard (transductive)
MRR0.376
14
Knowledge Graph CompletionNELL-995
MRR0.543
8
Knowledge Graph CompletionFamily
MRR99.2
7
Inductive Knowledge Graph CompletionNELL-995 v4
MRR31.7
7
Knowledge Graph CompletionWN18RR-ind v1
Hits@165.3
7
Inductive Knowledge Graph CompletionWN18RR V1
MRR0.7
7
Inductive Knowledge Graph CompletionWN18RR V2
MRR0.689
7
Inductive Knowledge Graph CompletionWN18RR V3
MRR42.9
7
Showing 10 of 29 rows

Other info

Follow for update