no code implementations • 14 Oct 2022 • Tiantian He, Haicang Zhou, Yew-Soon Ong, Gao Cong
We further propose Graph selective attention networks (SATs) to learn representations from the highly correlated node features identified and investigated by different SA mechanisms.
1 code implementation • 30 Jun 2020 • Shengzhong Zhang, Zengfeng Huang, Haicang Zhou, Ziang Zhou
A key of success to such contrastive learning methods is how to draw positive and negative samples.