zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Zifeng, Cai, Heling, Wu, Jingpei, Ma, Yunpu, Liao, Ruotong, Xiong, Bo, Tresp, Volker
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909137563025408
author Ding, Zifeng
Cai, Heling
Wu, Jingpei
Ma, Yunpu
Liao, Ruotong
Xiong, Bo
Tresp, Volker
author_facet Ding, Zifeng
Cai, Heling
Wu, Jingpei
Ma, Yunpu
Liao, Ruotong
Xiong, Bo
Tresp, Volker
contents Modeling evolving knowledge over temporal knowledge graphs (TKGs) has become a heated topic. Various methods have been proposed to forecast links on TKGs. Most of them are embedding-based, where hidden representations are learned to represent knowledge graph (KG) entities and relations based on the observed graph contexts. Although these methods show strong performance on traditional TKG forecasting (TKGF) benchmarks, they face a strong challenge in modeling the unseen zero-shot relations that have no prior graph context. In this paper, we try to mitigate this problem as follows. We first input the text descriptions of KG relations into large language models (LLMs) for generating relation representations, and then introduce them into embedding-based TKGF methods. LLM-empowered representations can capture the semantic information in the relation descriptions. This makes the relations, whether seen or unseen, with similar semantic meanings stay close in the embedding space, enabling TKGF models to recognize zero-shot relations even without any observed graph context. Experimental results show that our approach helps TKGF models to achieve much better performance in forecasting the facts with previously unseen relations, while still maintaining their ability in link forecasting regarding seen relations.
format Preprint
id arxiv_https___arxiv_org_abs_2311_10112
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
Ding, Zifeng
Cai, Heling
Wu, Jingpei
Ma, Yunpu
Liao, Ruotong
Xiong, Bo
Tresp, Volker
Artificial Intelligence
Computation and Language
Machine Learning
Modeling evolving knowledge over temporal knowledge graphs (TKGs) has become a heated topic. Various methods have been proposed to forecast links on TKGs. Most of them are embedding-based, where hidden representations are learned to represent knowledge graph (KG) entities and relations based on the observed graph contexts. Although these methods show strong performance on traditional TKG forecasting (TKGF) benchmarks, they face a strong challenge in modeling the unseen zero-shot relations that have no prior graph context. In this paper, we try to mitigate this problem as follows. We first input the text descriptions of KG relations into large language models (LLMs) for generating relation representations, and then introduce them into embedding-based TKGF methods. LLM-empowered representations can capture the semantic information in the relation descriptions. This makes the relations, whether seen or unseen, with similar semantic meanings stay close in the embedding space, enabling TKGF models to recognize zero-shot relations even without any observed graph context. Experimental results show that our approach helps TKGF models to achieve much better performance in forecasting the facts with previously unseen relations, while still maintaining their ability in link forecasting regarding seen relations.
title zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2311.10112