Add scripts for running gcn with dp & fix tensor under different device

[rayrayraykk]

As the title says.

[joneswong]

@DavdGao hi dawei, we are unfamiliar with this algorithm. Could you give an explanation for us about what is the (\epsilon, \delta) each single query (training round) satisfies, when we specify constant=1 and eps in {50, 500, 5000}? Thanks!

[DavdGao]

@DavdGao hi dawei, we are unfamiliar with this algorithm. Could you give an explanation for us about what is the (\epsilon, \delta) each single query (training round) satisfies, when we specify constant=1 and eps in {50, 500, 5000}? Thanks!

The $\epsilon-\delta$-DP guarantee promises given two neighbor dataset $D$ and $D'$, $P(M(D)\in S))\leq \exp{(\epsilon)} P(M(D)\in S) + \delta$, where $M$ is the training process in our setting. In NbAFL, the $\epsilon$ can be specified by the user, while $\delta$ is modified by the constant $c$.

[rayrayraykk]

please see the inline comments

Updated accordingly.