Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction
This work addresses the scalability and cost issues in knowledge graph link prediction for researchers and practitioners, though it is incremental as it builds on the existing KGT5 model.
The paper tackles the problem of link prediction in knowledge graphs by proposing KGT5-context, a sequence-to-sequence model that incorporates contextual neighborhood information, which eliminates the need for a separate large knowledge graph embedding model and achieves state-of-the-art performance with reduced model size.
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.