source code for "Modeling Heterogeneous Edges to Represent Networks with Graph Auto-Encoder", paper
we propose a regularized graph auto-encoders (RGAE) model, committed to utilizing abundant information in multiple views to learn robust network representations. More specifically, RGAE designs shared and private graph auto-encoders as main components to capture high-order nonlinear structure information of the networks. Besides, two loss functions serve as regularization to extract consistent and unique information, respectively.
python3.6 Tensorflow 1.12.0
python main.py -c ./config/aminer.ini