Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Open Access
- 4 August 2023
- conference paper
- Published by Association for Computing Machinery (ACM) in Proceedings of the Acm Sigkdd Conference on Knowledge Discovery and Data Mining
- Vol. 2023, 5270-5281
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 17 references indexed in Scilit:
- Pre-training on Large-Scale Heterogeneous Graph2021
- AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search2021
- TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search2021
- JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs2021
- GPT-GNN2020
- GCC2020
- Heterogeneous Graph Transformer2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- Graph Convolutional Networks for Text ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Heterogeneous Graph Attention Network2019