Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations

TL;DR

This paper introduces Time-LowFER, a low-rank tensor factorization model with a cycle-aware, model-agnostic time encoding scheme for improved temporal knowledge graph reasoning, achieving competitive results on benchmarks.

Contribution

It presents a novel, parameter-efficient extension of LowFER with a generalized time encoding scheme for temporal knowledge graphs.

Findings

Performs on par or better than state-of-the-art models

Effective in modeling time-aware knowledge graph data

Offers a unified, flexible framework for temporal reasoning

Abstract

Temporal knowledge graph completion (TKGC) has become a popular approach for reasoning over the event and temporal knowledge graphs, targeting the completion of knowledge with accurate but missing information. In this context, tensor decomposition has successfully modeled interactions between entities and relations. Their effectiveness in static knowledge graph completion motivates us to introduce Time-LowFER, a family of parameter-efficient and time-aware extensions of the low-rank tensor factorization model LowFER. Noting several limitations in current approaches to represent time, we propose a cycle-aware time-encoding scheme for time features, which is model-agnostic and offers a more generalized representation of time. We implement our methods in a unified temporal knowledge graph embedding framework, focusing on time-sensitive data processing. The experiments show that our proposed methods perform on par or better than the state-of-the-art semantic matching models on two benchmarks.