no code implementations • 20 Jun 2023 • Xiaojuan Zhang, Jun Fu, Shuang Li
Inspired by the success of contrastive learning, we propose a novel framework for contrastive disentangled learning on graphs, employing a disentangled graph encoder and two carefully crafted self-supervision signals.
no code implementations • 20 Jun 2023 • Jun Fu, Xiaojuan Zhang, Shuang Li, Dali Chen
The proposed framework infers the latent factors that cause edges in the graph and disentangles the representation into multiple channels corresponding to unique latent factors, which contributes to improving the performance of link prediction.