Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs

TL;DR

This paper introduces a novel end-to-end graph attention model for logical query answering over incomplete knowledge graphs, effectively handling variable contributions from different query paths and outperforming existing methods.

Contribution

The paper proposes the Contextual Graph Attention (CGA) model that jointly learns embeddings and query answering, introducing new large datasets for evaluation.

Findings

CGA outperforms baseline models on multiple datasets.

The model handles variable query path contributions effectively.

Fewer parameters are needed compared to previous models.

Abstract

Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of contributions from different query paths. We proposed to leverage a graph attention mechanism to handle the unequal contribution of different query paths. However, commonly used graph attention assumes that the center node embedding is provided, which is unavailable in this task since the center node is to be predicted. To solve this problem we propose a multi-head attention-based end-to-end logical query answering model, called Contextual Graph Attention model(CGA), which uses an initial neighborhood aggregation layer to generate the center embedding, and the whole model is trained jointly on the original KG structure as well as the sampled query-answer pairs. We also introduce two new datasets, DB18 and WikiGeo19, which are rather large in size compared to the existing datasets and contain many more relation types, and use them to evaluate the performance of the proposed model. Our result shows that the proposed CGA with fewer learnable parameters consistently outperforms the baseline models on both datasets as well as Bio dataset.