1 code implementation • 8 Sep 2023 • Eric Inae, Gang Liu, Meng Jiang
Attribute reconstruction is used to predict node or edge features in the pre-training of graph neural networks.
1 code implementation • 20 May 2023 • Gang Liu, Tong Zhao, Eric Inae, Tengfei Luo, Meng Jiang
The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels.
1 code implementation • 17 Mar 2023 • Gang Liu, Eric Inae, Tong Zhao, Jiaxin Xu, Tengfei Luo, Meng Jiang
A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks.