Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes

TL;DR

This paper introduces TIME2BOX, a novel knowledge base embedding framework that effectively handles both temporal and atemporal statements in knowledge graphs, improving link and time prediction accuracy.

Contribution

The paper presents TIME2BOX, a new method that models temporal scopes with boxes and intersections, addressing missing temporal information in knowledge bases.

Findings

Outperforms state-of-the-art methods on link prediction

Outperforms state-of-the-art methods on time prediction

Handles atemporal and temporal statements simultaneously

Abstract

Almost all statements in knowledge bases have a temporal scope during which they are valid. Hence, knowledge base completion (KBC) on temporal knowledge bases (TKB), where each statement \textit{may} be associated with a temporal scope, has attracted growing attention. Prior works assume that each statement in a TKB \textit{must} be associated with a temporal scope. This ignores the fact that the scoping information is commonly missing in a KB. Thus prior work is typically incapable of handling generic use cases where a TKB is composed of temporal statements with/without a known temporal scope. In order to address this issue, we establish a new knowledge base embedding framework, called TIME2BOX, that can deal with atemporal and temporal statements of different types simultaneously. Our main insight is that answers to a temporal query always belong to a subset of answers to a time-agnostic counterpart. Put differently, time is a filter that helps pick out answers to be correct during certain periods. We introduce boxes to represent a set of answer entities to a time-agnostic query. The filtering functionality of time is modeled by intersections over these boxes. In addition, we generalize current evaluation protocols on time interval prediction. We describe experiments on two datasets and show that the proposed method outperforms state-of-the-art (SOTA) methods on both link prediction and time prediction.