Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
This addresses the challenge of improving GNN-based models for link prediction in knowledge graphs, particularly for inductive scenarios where testing entities are unseen, representing a significant advancement in the field.
The paper tackles the problem of link prediction in knowledge graphs by introducing Context Pooling, a novel graph pooling method that generates query-specific graphs for inductive settings, achieving state-of-the-art performance in 42 out of 48 experimental settings.
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.