English

Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

Machine Learning 2023-06-01 v2 Artificial Intelligence Social and Information Networks

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.

Keywords

Cite

@article{arxiv.2305.13059,
  title  = {Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction},
  author = {Adrian Kochsiek and Apoorv Saxena and Inderjeet Nair and Rainer Gemulla},
  journal= {arXiv preprint arXiv:2305.13059},
  year   = {2023}
}

Comments

7 pages, 2 figures

R2 v1 2026-06-28T10:41:28.051Z