HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters
September 18, 2024 ยท View on GitHub
This repository contains the reference code for the manuscript ``HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters"
Contents
Installation
- pip install -r requirements.txt
- Unzip the datasets (can be found in ./dataset/)
- Unzip the pre-trained embedding (can be found in ./pre_trained_embedding)
Preparation
Important args:
--upload_paTest checkpoints to reproduce the results--datasetHeterogeneous graph: ACM, Yelp, DBLP, Aminer--custom_keyNode: node classification
Training
python main.py