Distance-Based Propagation for Efficient Knowledge Graph Reasoning

Harry Shomer, Yao Ma, Juanhui Li, Bo Wu, Charu C. Aggarwal, Jiliang Tang

Submission Type: Regular Long Paper

Submission Track: Machine Learning for NLP

Keywords: knowledge graphs, link prediction, graph neural network

TL;DR: We propose a new GNN for knowledge graphs that can efficiently aggregate path information.

Abstract: Knowledge graph completion (KGC) aims to predict unseen edges in knowledge graphs (KGs), resulting in the discovery of new facts. A new class of methods have been proposed to tackle this problem by aggregating path information. These methods have shown tremendous ability in the task of KGC. However they are plagued by efficiency issues. Though there are a few recent attempts to address this through learnable path pruning, they often sacrifice the performance to gain efficiency. In this work, we identify two intrinsic limitations of these methods that affect the efficiency and representation quality. To address the limitations, we introduce a new method, TAGNet, which is able to efficiently propagate information. This is achieved by only aggregating paths in a fixed window for each source-target pair. We demonstrate that the complexity of TAGNet is independent of the number of layers. Extensive experiments demonstrate that TAGNet can cut down on the number of propagated messages by as much as $90$% while achieving competitive performance on multiple KG datasets.

Submission Number: 4512