RETA: A Schema-Aware, End-to-End Solution for Instance Completion in Knowledge Graphs

Abstract

Knowledge Graph (KG) completion has been widely studied to tackle the incompleteness issue (i.e., missing facts) in modern KGs. A fact in a KG is represented as a triplet (ℎ, , ) linking two entities ℎ and via a relation . Existing work mostly consider link prediction to solve this problem, i.e., given two elements of a triplet predicting the missing one, such as (ℎ, , ?). This task has, however, a strong assumption on the two given elements in a triplet, which have to be correlated, resulting otherwise in meaningless predictions, such as (Marie Curie, headquarters location, ?). In addition, the KG completion problem has also been formulated as a relation prediction task, i.e., when predicting relations for a given entity ℎ. Without predicting , this task is however a step away from the ultimate goal of KG completion. Against this background, this paper studies an instance completion task suggesting -pairs for a given ℎ, i.e., (ℎ, ?, ?). We propose an end-to-end solution called RETA (as it suggests the Relation and Tail for a given head entity) consisting of two components: a RETA-Filter and RETA-Grader. More precisely, our RETA-Filter first generates candidate -pairs for a given ℎ by extracting and leveraging the schema of a KG; our RETA-Grader then evaluates and ranks the candidate -pairs considering the plausibility of both the candidate triplet and its corresponding schema using a newly-designed KG embedding model. We evaluate our methods against a sizable collection of state-of-the-art techniques on three real-world KG datasets. Results show that our RETA-Filter generates of high-quality candidate -pairs, outperforming the best baseline techniques while reducing by 10.61%-84.75% the candidate size under the same candidate quality guarantees. Moreover, our RETA-Grader also significantly outperforms state-of-the-art link prediction techniques on the instance completion task by 16.25%-65.92% across different datasets. * Corresponding author This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.

Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings

“…Knowledge Graph Embedding (KGE) represents entities and relations of knowledge graphs (KGs) in the semantic vector space, and has shown great potential in automatic KG completion and knowledge-driven tasks [15,16,31,33]. Given a query having an entity and the relation of a triple, a typical KGE model learns embedding vectors by predicting the missing entity from the whole entity set [30].…”