Time-aware Graph Embedding: A temporal smoothness and task-oriented approach

TL;DR

This paper introduces RTGE, a novel time-aware graph embedding method that incorporates temporal smoothness and task-oriented negative sampling, significantly improving performance in temporal knowledge graph tasks.

Contribution

RTGE uniquely integrates temporal smoothness and a task-oriented negative sampling strategy into graph embedding, enhancing temporal and structural representation capabilities.

Findings

RTGE outperforms existing methods on benchmark tasks.

Incorporating temporal smoothness improves embedding quality.

Task-oriented negative sampling enhances task-specific performance.

Abstract

Knowledge graph embedding, which aims to learn the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently. However, most knowledge graph embedding methods focus on the structural relationships in fixed triples while ignoring the temporal information. Currently, existing time-aware graph embedding methods only focus on the factual plausibility, while ignoring the temporal smoothness which models the interactions between a fact and its contexts, and thus can capture fine-granularity temporal relationships. This leads to the limited performance of embedding related applications. To solve this problem, this paper presents a Robustly Time-aware Graph Embedding (RTGE) method by incorporating temporal smoothness. Two major innovations of our paper are presented here. At first, RTGE integrates a measure of temporal smoothness in the learning process of the time-aware graph embedding. Via the proposed additional smoothing factor, RTGE can preserve both structural information and evolutionary patterns of a given graph. Secondly, RTGE provides a general task-oriented negative sampling strategy associated with temporally-aware information, which further improves the adaptive ability of the proposed algorithm and plays an essential role in obtaining superior performance in various tasks. Extensive experiments conducted on multiple benchmark tasks show that RTGE can increase performance in entity/relationship/temporal scoping prediction tasks.