Graph Structure Learning in GNN

We extract the definitions in Wu et al., 20201. Given node embeddings $\mathbf E_i$1,

$$ \begin{align} \mathbf M_i &= \tanh(\alpha \mathbf E_i \Theta_i) \\ \mathbf A &= \operatorname{ReLU}(\tanh(\alpha (\mathbf M_1 \mathbf M_2^T - \mathbf M_2\mathbf M_1^T))), \end{align} $$

The author also proposed sparse requirement and only take the top-$k$ largest elements in $A$.

Planted: by ;

L Ma (2022). 'Graph Structure Learning in GNN', Datumorphism, 11 April. Available at: