Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

TL;DR

This paper introduces KGT5-context, a simplified sequence-to-sequence model for knowledge graph link prediction that leverages local neighborhood context, reducing complexity and achieving state-of-the-art results without large embedding models.

Contribution

It demonstrates that incorporating local neighborhood context into KGT5 enhances link prediction performance, eliminating the need for large, costly embedding models.

Findings

KGT5-context achieves state-of-the-art LP performance.

Adding neighborhood context reduces model complexity.

Eliminates reliance on large embedding models.

Abstract

We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG). Our work expands on KGT5, a recent LP model that exploits textual features of the KG, has small model size, and is scalable. To reach good predictive performance, however, KGT5 relies on an ensemble with a knowledge graph embedding model, which itself is excessively large and costly to use. In this short paper, we show empirically that adding contextual information - i.e., information about the direct neighborhood of the query entity - alleviates the need for a separate KGE model to obtain good performance. The resulting KGT5-context model is simple, reduces model size significantly, and obtains state-of-the-art performance in our experimental study.