Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer

TL;DR

This paper introduces KGTransformer, a pretraining model for knowledge graphs that serves as a universal module for various KG-related tasks, utilizing self-supervised learning and prompt tuning to improve transferability and performance.

Contribution

The paper proposes KGTransformer, a novel pretraining framework with a prompt-tuning mechanism, providing a versatile and effective KRF module for diverse KG tasks.

Findings

KGTransformer outperforms task-specific models in experiments.

Pretraining with self-supervised tasks enhances transferability.

Prompt tuning enables flexible interaction with task data.

Abstract

Knowledge graphs (KG) are essential background knowledge providers in many tasks. When designing models for KG-related tasks, one of the key tasks is to devise the Knowledge Representation and Fusion (KRF) module that learns the representation of elements from KGs and fuses them with task representations. While due to the difference of KGs and perspectives to be considered during fusion across tasks, duplicate and ad hoc KRF modules design are conducted among tasks. In this paper, we propose a novel knowledge graph pretraining model KGTransformer that could serve as a uniform KRF module in diverse KG-related tasks. We pretrain KGTransformer with three self-supervised tasks with sampled sub-graphs as input. For utilization, we propose a general prompt-tuning mechanism regarding task data as a triple prompt to allow flexible interactions between task KGs and task data. We evaluate pretrained KGTransformer on three tasks, triple classification, zero-shot image classification, and question answering. KGTransformer consistently achieves better results than specifically designed task models. Through experiments, we justify that the pretrained KGTransformer could be used off the shelf as a general and effective KRF module across KG-related tasks. The code and datasets are available at https://github.com/zjukg/KGTransformer.