Question about batch training for Graph classification

hugochan / IDGL

Code & data accompanying the NeurIPS 2020 paper "Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings".

Apache License 2.0

223 stars 33 forks source link

Open PKUTAN opened 1 year ago

PKUTAN commented 1 year ago

Is IDGL able to train a batch of graph with different node numbers for a iteration?

yuanyz0825 commented 1 year ago

I achieve it! It is based on a batch round training.

2578562306 commented 18 hours ago

Is IDGL able to train a batch of graph with different node numbers for a iteration?

论文中公式形式就指出了，应该是基于批次训练的