Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs

TL;DR

This paper introduces Context Pooling, a novel graph pooling method for knowledge graphs that generates query-specific graphs, significantly improving inductive link prediction performance across multiple datasets.

Contribution

It is the first to apply graph pooling in knowledge graphs and to generate query-specific graphs for inductive link prediction, enhancing GNN effectiveness.

Findings

Achieved state-of-the-art results in 42 out of 48 settings.

Introduced neighborhood precision and recall metrics for relevance assessment.

Demonstrated the method's effectiveness on multiple datasets and models.

Abstract

Recent investigations on the effectiveness of Graph Neural Network (GNN)-based models for link prediction in Knowledge Graphs (KGs) show that vanilla aggregation does not significantly impact the model performance. In this paper, we introduce a novel method, named Context Pooling, to enhance GNN-based models' efficacy for link predictions in KGs. To our best of knowledge, Context Pooling is the first methodology that applies graph pooling in KGs. Additionally, Context Pooling is first-of-its-kind to enable the generation of query-specific graphs for inductive settings, where testing entities are unseen during training. Specifically, we devise two metrics, namely neighborhood precision and neighborhood recall, to assess the neighbors' logical relevance regarding the given queries, thereby enabling the subsequent comprehensive identification of only the logically relevant neighbors for link prediction. Our method is generic and assessed by being applied to two state-of-the-art (SOTA) models on three public transductive and inductive datasets, achieving SOTA performance in 42 out of 48 settings.