Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Authors:
- Han XieHXHan Xie
- Da ZhengDZDa Zheng
- Jun MaJMJun Ma
- Houyu ZhangHZHouyu Zhang
- Vassilis N. IoannidisVIVassilis N. Ioannidis
- Xiang SongXSXiang Song
- Qing PingQPQing Ping
- Sheng WangSWSheng Wang
- Carl YangCYCarl Yang
- Yi XuYXYi Xu
- Belinda ZengBZBelinda Zeng
- Trishul ChilimbiTCTrishul Chilimbi
Preprint
Abstract
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applications with different graph schemas. To address this problem, we propose a framework of graph-aware language model pre-training (GALM) on a large graph corpus, which incorporates large language models and graph neural networks, and a variety of fine-tuning methods on downstream applications. We conduct extensive experiments on Amazon's real internal datasets and large public datasets. Comprehensive empirical results and in-depth analysis demonstrate the effectiveness of our proposed methods along with lessons learned.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A SurveyACM Computing Surveys, 2023
- KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language RepresentationTransactions of the Association for Computational Linguistics, 2021
- Heterogeneous Network Representation Learning: A Unified Framework With Survey and BenchmarkIEEE Transactions on Knowledge and Data Engineering, 2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019