"*Let's test what you've learned. Feel free to [](https://colab.research.google.com/github/dmlc/dgl/blob/master/notebooks/sparse/quickstart.ipynb).*\n",
"*Let's test what you've learned. Feel free to [](https://colab.research.google.com/github/dmlc/dgl/blob/master/notebooks/sparse/quickstart.ipynb).*\n",
"\n",
"\n",
"Given a sparse symmetrical adjacency matrix $A$, calculate its symmetrically normalized adjacency matrix: $$norm = \\bar{D}^{-\\frac{1}{2}}\\bar{A}\\bar{D}^{-\\frac{1}{2}}$$\n",
"Given a sparse symmetrical adjacency matrix $A$, calculate its symmetrically normalized adjacency matrix: $$norm = \\bar{D}^{-\\frac{1}{2}}\\bar{A}\\bar{D}^{-\\frac{1}{2}}$$\n",
...
@@ -1224,7 +1217,7 @@
...
@@ -1224,7 +1217,7 @@
"Where $\\bar{A} = A + I$, $I$ is the identity matrix, and $\\bar{D}$ is the diagonal node degree matrix of $\\bar{A}$."
"Where $\\bar{A} = A + I$, $I$ is the identity matrix, and $\\bar{D}$ is the diagonal node degree matrix of $\\bar{A}$."
],
],
"metadata": {
"metadata": {
"id": "yDQ4Kmr_08St"
"id": "1iBNlJVYz3zi"
}
}
},
},
{
{
...
@@ -1254,7 +1247,7 @@
...
@@ -1254,7 +1247,7 @@
{
{
"cell_type": "markdown",
"cell_type": "markdown",
"source": [
"source": [
"## Exercise\n",
"## Exercise \\#2\n",
"\n",
"\n",
"Let's implement a simplified version of the Graph Attention Network (GAT) layer.\n",
"Let's implement a simplified version of the Graph Attention Network (GAT) layer.\n",