RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion

TL;DR

RTFE is a recursive framework that enhances temporal knowledge graph completion by modeling state transitions as a Markov chain, effectively leveraging static embeddings for dynamic graph evolution.

Contribution

It introduces a recursive method to adapt static knowledge graph embeddings for temporal graphs, improving TKG completion performance.

Findings

Effective on five TKG datasets

Outperforms existing TKGE models

Models state transitions as gradient updates

Abstract

Static knowledge graph (SKG) embedding (SKGE) has been studied intensively in the past years. Recently, temporal knowledge graph (TKG) embedding (TKGE) has emerged. In this paper, we propose a Recursive Temporal Fact Embedding (RTFE) framework to transplant SKGE models to TKGs and to enhance the performance of existing TKGE models for TKG completion. Different from previous work which ignores the continuity of states of TKG in time evolution, we treat the sequence of graphs as a Markov chain, which transitions from the previous state to the next state. RTFE takes the SKGE to initialize the embeddings of TKG. Then it recursively tracks the state transition of TKG by passing updated parameters/features between timestamps. Specifically, at each timestamp, we approximate the state transition as the gradient update process. Since RTFE learns each timestamp recursively, it can naturally transit to future timestamps. Experiments on five TKG datasets show the effectiveness of RTFE.