OpenHGNN

OpenHGNN copied to clipboard

RMR 模型全称为 Reserving-Masking-Reconstruction 模型， RMR 模型突破了传统基于 metapath 的限制，通过信息保留、关系子图 mask 和反向关系重构三大模块，实现了在大规模异构图上高效且有效的自监督表示学习。实验结果表明，该方法在性能和计算资源方面均表现优异。

Yanghaolan0

## ❓ Questions and Help Are background information or descriptions available for the interface's baseline dataset, except for the risk commodity dataset and the delivery prediction dataset? Or are there...

nklsKrmnn

## 🐛 Bug when I run codes below from openhgnn.experiment import Experiment experiment = Experiment(model='CompGCN', dataset='acm4GTN', task='node_classification', gpu=-1, lr=0.05, hidden_dim=64, max_epoch=30, num_layers=3) experiment.run() I got failed. Traceback follows: Traceback (most...

1BIMU

## ❓ Questions and Help Hello, we are trying to use OpenHGNN to benchmark different heterogeneous graph neural networks. However, we cannot seem to be able to run openHGNN, as...

andrewkrapivin

when i run "python main.py -m HetGNN -t node_classification -d academic4HetGNN -g 0" to train my hetgnn model, I encounter this error > File "/root/OpenHGNN/openhgnn/trainerflow/hetgnn_trainer.py", line 78, in _full_train_setp >...

herbertguoqi