Temporal Knowledge Graph Completion using Box Embeddings

TL;DR

This paper introduces BoxTE, a novel box embedding model for temporal knowledge graph completion, which is fully expressive and achieves state-of-the-art results on benchmark datasets.

Contribution

The paper proposes BoxTE, a new box embedding approach for TKGC that extends BoxE, with improved expressiveness and inductive capacity for temporal data.

Findings

BoxTE achieves state-of-the-art performance on TKGC benchmarks.

BoxTE is fully expressive and has strong inductive capacity.

Empirical evaluation confirms the effectiveness of BoxTE.

Abstract

Knowledge graph completion is the task of inferring missing facts based on existing data in a knowledge graph. Temporal knowledge graph completion (TKGC) is an extension of this task to temporal knowledge graphs, where each fact is additionally associated with a time stamp. Current approaches for TKGC primarily build on existing embedding models which are developed for (static) knowledge graph completion, and extend these models to incorporate time, where the idea is to learn latent representations for entities, relations, and timestamps and then use the learned representations to predict missing facts at various time steps. In this paper, we propose BoxTE, a box embedding model for TKGC, building on the static knowledge graph embedding model BoxE. We show that BoxTE is fully expressive, and possesses strong inductive capacity in the temporal setting. We then empirically evaluate our model and show that it achieves state-of-the-art results on several TKGC benchmarks.