AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning

TL;DR

AdaProp introduces an adaptive, learning-based propagation mechanism for GNNs on knowledge graphs, effectively filtering irrelevant entities and improving reasoning efficiency and accuracy.

Contribution

It proposes a novel adaptive propagation path learning method that dynamically filters entities, addressing limitations of fixed paths and reducing complexity in GNN-based KG reasoning.

Findings

Outperforms existing methods in reasoning accuracy.

Reduces computational complexity with linear sampling.

Demonstrates semantic awareness in entity filtering.

Abstract

Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient, and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.