[Doc] Update colab tutorials with spmatrix (#5220)

* Created using Colaboratory * Created using Colaboratory * Created using Colaboratory * Created using Colaboratory * Created using Colaboratory * Created using Colaboratory

[Doc] Update colab tutorials with spmatrix (#5220)
* Created using Colaboratory * Created using Colaboratory * Created using Colaboratory * Created using Colaboratory * Created using Colaboratory * Created using Colaboratory
0bdc437b · Minjie Wang · GitHub · fbbe6d61 · 0bdc437b · 0bdc437b
Unverified Commit 0bdc437b authored Jan 20, 2023 by Minjie Wang Committed by GitHub Jan 20, 2023
5 changed files
--- a/notebooks/sparse/gcn.ipynb
+++ b/notebooks/sparse/gcn.ipynb
@@ -54,7 +54,7 @@
        "id": "FTqB360eRvya",
        "outputId": "df54b94e-fd1b-4b96-fca1-21948284254c"
      },
-      "execution_count": 2,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -71,7 +71,9 @@
        "## Graph Convolutional Layer\n",
        "\n",
        "Mathematically, the graph convolutional layer is defined as:\n",
-        "$$f(X^{(l)}, A) = \\sigma(\\hat{D}^{-\\frac{1}{2}}\\hat{A}\\hat{D}^{-\\frac{1}{2}}X^{(l)}W^{(l)})$$",
+        "\n",
+        "$$f(X^{(l)}, A) = \\sigma(\\hat{D}^{-\\frac{1}{2}}\\hat{A}\\hat{D}^{-\\frac{1}{2}}X^{(l)}W^{(l)})$$\n",
+        "\n",
        "with $\\hat{A} = A + I$, where $A$ denotes the adjacency matrix and $I$ denotes the identity matrix, $\\hat{D}$ refers to the diagonal node degree matrix of $\\hat{A}$ and $W^{(l)}$ denotes a trainable weight matrix. $\\sigma$ refers to a non-linear activation (e.g. relu).\n",
        "\n",
        "The code below shows how to implement it using the `dgl.sparse` package. The core operations are:\n",
@@ -114,7 +116,7 @@
      "metadata": {
        "id": "Y4I4EhHQ_kKb"
      },
-      "execution_count": 3,
+      "execution_count": null,
      "outputs": []
    },
    {
@@ -144,7 +146,7 @@
      "metadata": {
        "id": "BHX3vRjDWJTO"
      },
-      "execution_count": 4,
+      "execution_count": null,
      "outputs": []
    },
    {
@@ -179,9 +181,9 @@
        "    loss_fcn = nn.CrossEntropyLoss()\n",
        "\n",
        "    # Preprocess to get the adjacency matrix of the graph.\n",
-        "    src, dst = g.edges()\n",
+        "    indices = torch.stack(g.edges())\n",
        "    N = g.num_nodes()\n",
-        "    A = dglsp.from_coo(dst, src, shape=(N, N))\n",
+        "    A = dglsp.spmatrix(indices, shape=(N, N))\n",
        "\n",
        "    for epoch in range(100):\n",
        "        model.train()\n",
@@ -229,7 +231,7 @@
        },
        "outputId": "552e2c22-44f4-4495-c7f9-a57f13484270"
      },
-      "execution_count": 5,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -280,4 +282,4 @@
      }
    }
  ]
-}
+}
\ No newline at end of file
--- a/notebooks/sparse/graph_diffusion.ipynb
+++ b/notebooks/sparse/graph_diffusion.ipynb
@@ -31,7 +31,7 @@
    },
    {
      "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
      "metadata": {
        "id": "F6eQWmWn7lqh",
        "colab": {
@@ -101,9 +101,9 @@
        "dgl_g = dataset[0]\n",
        "\n",
        "# Get its adjacency matrix.\n",
-        "src, dst = dgl_g.edges()\n",
+        "indices = torch.stack(dgl_g.edges())\n",
        "N = dgl_g.num_nodes()\n",
-        "A = dglsp.from_coo(dst, src, shape=(N, N))\n",
+        "A = dglsp.spmatrix(indices, shape=(N, N))\n",
        "print(A.to_dense())"
      ],
      "metadata": {
@@ -113,7 +113,7 @@
        "id": "_TnCECJmBKJE",
        "outputId": "d8b78f0b-3a1c-4a9e-bcc9-ed4df7b7b5b7"
      },
-      "execution_count": 2,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -134,7 +134,9 @@
      "cell_type": "markdown",
      "source": [
        "We use the graph convolution matrix from Graph Convolution Networks as the diffusion matrix in this example. The graph convolution matrix is defined as:\n",
-        "$$\\tilde{A} = \\hat{D}^{-\\frac{1}{2}}\\hat{A}\\hat{D}^{-\\frac{1}{2}}$$",
+        "\n",
+        "$$\\tilde{A} = \\hat{D}^{-\\frac{1}{2}}\\hat{A}\\hat{D}^{-\\frac{1}{2}}$$\n",
+        "\n",
        "with $\\hat{A} = A + I$, where $A$ denotes the adjacency matrix and $I$ denotes the identity matrix, $\\hat{D}$ refers to the diagonal node degree matrix of $\\hat{A}$."
      ],
      "metadata": {
@@ -159,7 +161,7 @@
        "id": "JyzctBGaC_O5",
        "outputId": "b03ef3dc-dcf5-494e-9191-30591d09f138"
      },
-      "execution_count": 3,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -204,7 +206,7 @@
      "metadata": {
        "id": "DXb0uKqXDZKb"
      },
-      "execution_count": 4,
+      "execution_count": null,
      "outputs": []
    },
    {
@@ -249,7 +251,7 @@
        },
        "outputId": "be93263e-2283-4db7-caff-2e15e75ceb02"
      },
-      "execution_count": 5,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
@@ -5601,7 +5603,7 @@
      "metadata": {
        "id": "__U3Hsp_S0SR"
      },
-      "execution_count": 6,
+      "execution_count": null,
      "outputs": []
    },
    {
@@ -5678,9 +5680,9 @@
        "\n",
        "# Create the sparse adjacency matrix A (note that W was used as the notation\n",
        "# for adjacency matrix in the original paper).\n",
-        "src, dst = g.edges()\n",
+        "indices = torch.stack(g.edges())\n",
        "N = g.num_nodes()\n",
-        "A = dglsp.from_coo(dst, src, shape=(N, N))\n",
+        "A = dglsp.spmatrix(indices, shape=(N, N))\n",
        "\n",
        "# Calculate the graph convolution matrix.\n",
        "I = dglsp.identity(A.shape, device=dev)\n",
@@ -5708,7 +5710,7 @@
        },
        "outputId": "19e86f6a-c7f1-4b40-8cfc-58a181fc30d7"
      },
-      "execution_count": 7,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -5754,4 +5756,4 @@
      }
    }
  ]
-}
+}
\ No newline at end of file
--- a/notebooks/sparse/graph_transformer.ipynb
+++ b/notebooks/sparse/graph_transformer.ipynb
@@ -227,9 +227,9 @@
        "        )\n",
        "\n",
        "    def forward(self, g, X, pos_enc):\n",
-        "        src, dst = g.edges()\n",
+        "        indices = torch.stack(g.edges())\n",
        "        N = g.num_nodes()\n",
-        "        A = dglsp.from_coo(dst, src, shape=(N, N))\n",
+        "        A = dglsp.spmatrix(indices, shape=(N, N))\n",
        "        h = self.atom_encoder(X) + self.pos_linear(pos_enc)\n",
        "        for layer in self.layers:\n",
        "            h = layer(A, h)\n",
@@ -418,4 +418,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}
\ No newline at end of file
--- a/notebooks/sparse/hgnn.ipynb
+++ b/notebooks/sparse/hgnn.ipynb
@@ -57,7 +57,7 @@
        "id": "__2tKqL0eaB0",
        "outputId": "5b5106f6-074b-42a5-fc4c-4936efd2cef8"
      },
-      "execution_count": 1,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -108,9 +108,9 @@
        "import dgl.sparse as dglsp\n",
        "import torch\n",
        "\n",
-        "H = dglsp.from_coo(\n",
-        "    torch.LongTensor([0, 1, 2, 2, 2, 2, 3, 4, 5, 5, 5, 5, 6, 7, 7, 8, 8, 9, 9, 10]),\n",
-        "    torch.LongTensor([0, 0, 0, 1, 3, 4, 2, 1, 0, 2, 3, 4, 2, 1, 3, 1, 3, 2, 4, 4])\n",
+        "H = dglsp.spmatrix(\n",
+        "    torch.LongTensor([[0, 1, 2, 2, 2, 2, 3, 4, 5, 5, 5, 5, 6, 7, 7, 8, 8, 9, 9, 10],\n",
+        "                      [0, 0, 0, 1, 3, 4, 2, 1, 0, 2, 3, 4, 2, 1, 3, 1, 3, 2, 4, 4]])\n",
        ")\n",
        "\n",
        "print(H.to_dense())"
@@ -122,7 +122,7 @@
        },
        "outputId": "a1a576f6-1559-479c-9f3e-93e41a56833d"
      },
-      "execution_count": 2,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -168,7 +168,7 @@
        },
        "outputId": "ffe2c441-8c2c-48a7-cef2-4ef6e96548ec"
      },
-      "execution_count": 3,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -187,8 +187,9 @@
        "## Hypergraph Neural Network (HGNN) Layer\n",
        "\n",
        "The [HGNN layer](https://arxiv.org/pdf/1809.09401.pdf) is defined as:\n",
-        "$$f(X^{(l)}, H; W^{(l)}) = \\sigma(L X^{(l)} W^{(l)})$$",
-        "$$L = D_v^{-1/2} H B D_e^{-1} H^\\top D_v^{-1/2}$$",
+        "\n",
+        "$$f(X^{(l)}, H; W^{(l)}) = \\sigma(L X^{(l)} W^{(l)})$$$$L = D_v^{-1/2} H B D_e^{-1} H^\\top D_v^{-1/2}$$\n",
+        "\n",
        "where\n",
        "* $H \\in \\mathbb{R}^{N \\times M}$ is the incidence matrix of hypergraph with $N$ nodes and $M$ hyperedges.\n",
        "* $D_v \\in \\mathbb{R}^{N \\times N}$ is a diagonal matrix representing node degrees, whose $i$-th diagonal element is $\\sum_{j=1}^M H_{ij}$.\n",
@@ -247,7 +248,7 @@
      "metadata": {
        "id": "58WnPtPvT2mx"
      },
-      "execution_count": 4,
+      "execution_count": null,
      "outputs": []
    },
    {
@@ -272,8 +273,8 @@
        "    dataset = CoraGraphDataset()\n",
        "\n",
        "    graph = dataset[0]\n",
-        "    src, dst = graph.edges()\n",
-        "    H = dglsp.from_coo(dst, src)\n",
+        "    indices = torch.stack(graph.edges())\n",
+        "    H = dglsp.spmatrix(indices)\n",
        "    H = H + dglsp.identity(H.shape)\n",
        "\n",
        "    X = graph.ndata[\"feat\"]\n",
@@ -286,7 +287,7 @@
      "metadata": {
        "id": "qI0j1J9pwTFg"
      },
-      "execution_count": 5,
+      "execution_count": null,
      "outputs": []
    },
    {
@@ -354,7 +355,7 @@
        "id": "IfEc6JRXwHPt",
        "outputId": "0172578a-6a1b-49eb-adcb-77ee1a949186"
      },
-      "execution_count": 6,
+      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
@@ -406,4 +407,4 @@
      }
    }
  ]
-}
+}
\ No newline at end of file
--- a/notebooks/sparse/quickstart.ipynb
+++ b/notebooks/sparse/quickstart.ipynb