"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This demo demonstrates how to perform unsupervised training of a GCN, GAT, APPNP, or GraphSAGE model using the Deep Graph Infomax algorithm (https://arxiv.org/pdf/1809.10341.pdf) on the CORA dataset. \n",
"\n",
"As with all StellarGraph workflows: first we load the dataset, next we create our data generators, and then we train our model. We then take the embeddings created through unsupervised training and predict the node classes using logistic regression."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"nbsphinx": "hidden",
"tags": [
"CloudRunner"
]
},
"outputs": [],
"source": [
"# install StellarGraph if running on Google Colab\n",
"import sys\n",
"if 'google.colab' in sys.modules:\n",
" %pip install -q stellargraph[demos]==1.0.0"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"nbsphinx": "hidden",
"tags": [
"VersionCheck"
]
},
"outputs": [],
"source": [
"# verify that we're using the correct version of StellarGraph for this notebook\n",
"import stellargraph as sg\n",
"\n",
"try:\n",
" sg.utils.validate_notebook_version(\"1.0.0\")\n",
"except AttributeError:\n",
" raise ValueError(\n",
" f\"This notebook requires StellarGraph version 1.0.0, but a different version {sg.__version__} is installed. Please see .\"\n",
" ) from None"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from stellargraph.mapper import (\n",
" CorruptedGenerator,\n",
" FullBatchNodeGenerator,\n",
" GraphSAGENodeGenerator,\n",
" HinSAGENodeGenerator,\n",
")\n",
"from stellargraph import StellarGraph\n",
"from stellargraph.layer import GCN, DeepGraphInfomax, GraphSAGE, GAT, APPNP, HinSAGE\n",
"\n",
"from stellargraph import datasets\n",
"from stellargraph.utils import plot_history\n",
"\n",
"import pandas as pd\n",
"from matplotlib import pyplot as plt\n",
"from sklearn import model_selection\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.manifold import TSNE\n",
"from IPython.display import display, HTML\n",
"\n",
"from tensorflow.keras.optimizers import Adam\n",
"from tensorflow.keras.callbacks import EarlyStopping\n",
"import tensorflow as tf\n",
"from tensorflow.keras import Model"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": [
"DataLoadingLinks"
]
},
"source": [
"(See [the \"Loading from Pandas\" demo](../basics/loading-pandas.ipynb) for details on how data can be loaded.)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"tags": [
"DataLoading"
]
},
"outputs": [
{
"data": {
"text/html": [
"The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words."
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"dataset = datasets.Cora()\n",
"display(HTML(dataset.description))\n",
"G, node_subjects = dataset.load()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Data Generators\n",
"\n",
"Now we create the data generators using `CorruptedGenerator`. `CorruptedGenerator` returns shuffled node features along with the regular node features and we train our model to discriminate between the two. \n",
"\n",
"Note that:\n",
"\n",
"- We typically pass all nodes to `corrupted_generator.flow` because this is an unsupervised task\n",
"- We don't pass `targets` to `corrupted_generator.flow` because these are binary labels (true nodes, false nodes) that are created by `CorruptedGenerator`"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Using GCN (local pooling) filters...\n"
]
}
],
"source": [
"fullbatch_generator = FullBatchNodeGenerator(G, sparse=False)\n",
"gcn_model = GCN(layer_sizes=[128], activations=[\"relu\"], generator=fullbatch_generator)\n",
"\n",
"corrupted_generator = CorruptedGenerator(fullbatch_generator)\n",
"gen = corrupted_generator.flow(G.nodes())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Model Creation and Training\n",
"\n",
"We create and train our `DeepGraphInfomax` model. Note that the loss used here must always be `tf.nn.sigmoid_cross_entropy_with_logits`."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"infomax = DeepGraphInfomax(gcn_model, corrupted_generator)\n",
"x_in, x_out = infomax.in_out_tensors()\n",
"\n",
"model = Model(inputs=x_in, outputs=x_out)\n",
"model.compile(loss=tf.nn.sigmoid_cross_entropy_with_logits, optimizer=Adam(lr=1e-3))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"tags": [
"parameters"
]
},
"outputs": [],
"source": [
"epochs = 100"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ['...']\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"es = EarlyStopping(monitor=\"loss\", min_delta=0, patience=20)\n",
"history = model.fit(gen, epochs=epochs, verbose=0, callbacks=[es])\n",
"plot_history(history)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Extracting Embeddings and Logistic Regression\n",
"\n",
"Since we've already trained the weights of our base model - GCN in this example - we can simply use `base_model.in_out_tensors` to obtain the trained node embedding model. Then we use logistic regression on the node embeddings to predict which class the node belongs to.\n",
"\n",
"Note that the results here differ from the paper due to different train/test/val splits."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"x_emb_in, x_emb_out = gcn_model.in_out_tensors()\n",
"\n",
"# for full batch models, squeeze out the batch dim (which is 1)\n",
"x_out = tf.squeeze(x_emb_out, axis=0)\n",
"emb_model = Model(inputs=x_emb_in, outputs=x_out)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Test classification accuracy: 0.7981952420016407\n"
]
}
],
"source": [
"train_subjects, test_subjects = model_selection.train_test_split(\n",
" node_subjects, train_size=0.1, test_size=None, stratify=node_subjects\n",
")\n",
"\n",
"test_gen = fullbatch_generator.flow(test_subjects.index)\n",
"train_gen = fullbatch_generator.flow(train_subjects.index)\n",
"\n",
"test_embeddings = emb_model.predict(test_gen)\n",
"train_embeddings = emb_model.predict(train_gen)\n",
"\n",
"lr = LogisticRegression(multi_class=\"auto\", solver=\"lbfgs\")\n",
"lr.fit(train_embeddings, train_subjects)\n",
"\n",
"y_pred = lr.predict(test_embeddings)\n",
"gcn_acc = (y_pred == test_subjects).mean()\n",
"print(f\"Test classification accuracy: {gcn_acc}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This accuracy is close to that for [training a supervised GCN model end-to-end](../node-classification/gcn-node-classification.ipynb), suggesting that Deep Graph Infomax is an effective method for unsupervised training."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Visualisation with TSNE\n",
"\n",
"Here we visualize the node embeddings with TSNE. As you can see below, the Deep Graph Infomax model produces well separated embeddings using unsupervised training."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"all_embeddings = emb_model.predict(fullbatch_generator.flow(G.nodes()))\n",
"\n",
"y = node_subjects.astype(\"category\")\n",
"trans = TSNE(n_components=2)\n",
"emb_transformed = pd.DataFrame(trans.fit_transform(all_embeddings), index=G.nodes())\n",
"emb_transformed[\"label\"] = y"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"alpha = 0.7\n",
"\n",
"fig, ax = plt.subplots(figsize=(7, 7))\n",
"ax.scatter(\n",
" emb_transformed[0],\n",
" emb_transformed[1],\n",
" c=emb_transformed[\"label\"].cat.codes,\n",
" cmap=\"jet\",\n",
" alpha=alpha,\n",
")\n",
"ax.set(aspect=\"equal\", xlabel=\"$X_1$\", ylabel=\"$X_2$\")\n",
"plt.title(\"TSNE visualization of GCN embeddings for cora dataset\")\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Comparing Different Models\n",
"\n",
"Now we run Deep Graph Infomax training for GAT, GCN, APPNP, and GraphSAGE. Note that switching between StellarGraph models only requires a few code changes."
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"def run_deep_graph_infomax(base_model, generator, epochs):\n",
" corrupted_generator = CorruptedGenerator(generator)\n",
" gen = corrupted_generator.flow(G.nodes())\n",
" infomax = DeepGraphInfomax(base_model, corrupted_generator)\n",
"\n",
" x_in, x_out = infomax.in_out_tensors()\n",
"\n",
" model = Model(inputs=x_in, outputs=x_out)\n",
" model.compile(loss=tf.nn.sigmoid_cross_entropy_with_logits, optimizer=Adam(lr=1e-3))\n",
" history = model.fit(gen, epochs=epochs, verbose=0, callbacks=[es])\n",
"\n",
" x_emb_in, x_emb_out = base_model.in_out_tensors()\n",
" # for full batch models, squeeze out the batch dim (which is 1)\n",
" if isinstance(base_model, (GAT, GCN, APPNP)):\n",
" x_emb_out = tf.squeeze(x_emb_out, axis=0)\n",
"\n",
" emb_model = Model(inputs=x_emb_in, outputs=x_emb_out)\n",
"\n",
" test_gen = generator.flow(test_subjects.index)\n",
" train_gen = generator.flow(train_subjects.index)\n",
"\n",
" test_embeddings = emb_model.predict(test_gen)\n",
" train_embeddings = emb_model.predict(train_gen)\n",
"\n",
" lr = LogisticRegression(multi_class=\"auto\", solver=\"lbfgs\")\n",
" lr.fit(train_embeddings, train_subjects)\n",
"\n",
" y_pred = lr.predict(test_embeddings)\n",
" acc = (y_pred == test_subjects).mean()\n",
"\n",
" return acc"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ['...']\n",
"Test classification accuracy: 0.448318293683347\n"
]
}
],
"source": [
"gat_model = GAT(\n",
" layer_sizes=[128], activations=[\"relu\"], generator=fullbatch_generator, attn_heads=8,\n",
")\n",
"gat_acc = run_deep_graph_infomax(gat_model, fullbatch_generator, epochs=epochs)\n",
"\n",
"gat_acc\n",
"print(f\"Test classification accuracy: {gat_acc}\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ['...']\n",
"Test classification accuracy: 0.4470877768662838\n"
]
}
],
"source": [
"appnp_model = APPNP(\n",
" layer_sizes=[128], activations=[\"relu\"], generator=fullbatch_generator\n",
")\n",
"appnp_acc = run_deep_graph_infomax(appnp_model, fullbatch_generator, epochs=epochs)\n",
"\n",
"print(f\"Test classification accuracy: {appnp_acc}\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ['...']\n",
"Test classification accuracy: 0.7013945857260049\n"
]
}
],
"source": [
"graphsage_generator = GraphSAGENodeGenerator(G, batch_size=1000, num_samples=[5])\n",
"\n",
"graphsage_model = GraphSAGE(\n",
" layer_sizes=[128], activations=[\"relu\"], generator=graphsage_generator\n",
")\n",
"graphsage_acc = run_deep_graph_infomax(\n",
" graphsage_model, graphsage_generator, epochs=epochs\n",
")\n",
"\n",
"print(f\"Test classification accuracy: {graphsage_acc}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Heteogeneous models\n",
"\n",
"Cora is a homogeneous graph, with only one type of node (`paper`) and one type of edge (`type`). Models designed for heterogeneous graphs (with moer than one of either) can also be applied to homogeneous graphs, but it is not using their additional flexibility.\n",
"\n",
"HinSAGE is a generalisation of GraphSAGE to heterogeneous graphs that can be trained with Deep Graph Infomax. For homogeneous graphs, it is equivalent to GraphSAGE and it indeed gives similar results."
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ['...']\n",
"Test classification accuracy: 0.7038556193601313\n"
]
}
],
"source": [
"hinsage_generator = HinSAGENodeGenerator(\n",
" G, batch_size=1000, num_samples=[5], head_node_type=\"paper\"\n",
")\n",
"\n",
"hinsage_model = HinSAGE(\n",
" layer_sizes=[128], activations=[\"relu\"], generator=hinsage_generator\n",
")\n",
"hinsage_acc = run_deep_graph_infomax(hinsage_model, hinsage_generator, epochs=epochs)\n",
"\n",
"print(f\"Test classification accuracy: {hinsage_acc}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Overall results\n",
"\n",
"The cell below shows the accuracy of each model."
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"