Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding

TL;DR

This paper introduces PTBox, a novel temporal knowledge graph embedding method that models arbitrary timestamps using polynomial decomposition and box embeddings, enabling better temporal reasoning and inference.

Contribution

The paper proposes a new approach combining polynomial-based temporal representation with box embeddings to improve modeling of arbitrary timestamps and inference in TKGs.

Findings

PTBox effectively encodes arbitrary timestamps including unseen ones.

It captures complex inference patterns and higher-arity relations.

Experimental results show superior performance on real-world datasets.

Abstract

Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately. However, existing TKG approaches still face two main challenges, i.e., the limited capability to model arbitrary timestamps continuously and the lack of rich inference patterns under temporal constraints. In this paper, we propose an innovative TKGE method (PTBox) via polynomial decomposition-based temporal representation and box embedding-based entity representation to tackle the above-mentioned problems. Specifically, we decompose time information by polynomials and then enhance the model's capability to represent arbitrary timestamps flexibly by incorporating the learnable temporal basis tensor. In addition, we model every entity as a hyperrectangle box and define each relation as a transformation on the head and tail entity boxes. The entity boxes can capture complex geometric structures and learn robust representations, improving the model's inductive capability for rich inference patterns. Theoretically, our PTBox can encode arbitrary time information or even unseen timestamps while capturing rich inference patterns and higher-arity relations of the knowledge base. Extensive experiments on real-world datasets demonstrate the effectiveness of our method.