An official source code for paper "Learning Generalizable Contrastive Representations for Graph Zero-shot Learning" [pdf] [Accepted by TMM] by Siyu Yi, Zhengyang Mao, Kangjie Zheng, Zhiping Xiao, Chong Chen, Xian-Sheng Hua, Yongdao Zhou, Ming Zhang, and Wei Ju.
The proposed GraphGCR is implemented with python 3.9.12 on a NVIDIA 2204 GPU.
Python package information is summarized as
- torch == 1.7.1
- numpy == 1.21.5
- scipy == 1.7.3
- torch_geometric == 1.7.1
To reproduce the results, unzip the datasets.zip and create a result folder, then run run.py.
If you use code or datasets in this repository for your research, please cite our paper.
For questions, comments, or remarks about the code please contact Siyu Yi ([email protected]). If you find this repository useful to your research or work, it is really appreciate to star this repository.