Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
fengxun705612 d838244a34 | 1 year ago | |
---|---|---|
.. | ||
scripts | 1 year ago | |
src | 1 year ago | |
README.md | 1 year ago | |
__init__.py | 1 year ago | |
requirements.txt | 1 year ago | |
train_lgtn.py | 1 year ago | |
utils.py | 1 year ago |
Graph Isomorphism Network(GIN) was proposed in 2020 and designed to evaluate graph outlier detection: Peculiar observations and new insights. In order to better play the role of the GIN network, combine it with the transformer network and use Laplacian as an auxiliary encoder.
More detail about GIN and Transformer can be found in:
L. Zhao and L. Akoglu, “On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights,” arXiv preprint arXiv:2012.12931, 2020.
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Advances in Neural Information Processing Systems. 2017: 5998-6008.
This repository contains a implementation of LGTN based on MindSpore and GraphLearning.
The experiment is based on ogbg-molpcba, which is a molecular dataset sampled from PubChem BioAssay. It is a graph prediction dataset from the Open Graph Benchmark (OGB).
CUDA_VISIBLE_DEVICES=0 python recommendation/lp_graphtrans/train_lgtn.py
ogbg-molpcba dataset
MindSpore Graph Learning is an efficient and easy-to-use graph learning framework, which allows researchers and developers to implement graph models according to formula easily and train efficiently.
https://gitee.com/mindspore/graphlearning
Python Vue TypeScript Markdown Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》