{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Node classification with Node2Vec using Stellargraph components" ] }, { "cell_type": "markdown", "metadata": { "nbsphinx": "hidden", "tags": [ "CloudRunner" ] }, "source": [ "
Run the latest release of this notebook:
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This example demonstrates how to perform node classification with Node2Vec using the Stellargraph components. This uses a keras implementation of Node2Vec available in stellargraph instead of the reference implementation provided by ``gensim``.\n", "\n", "\n", "**References**\n", "\n", "[1] Node2Vec: Scalable Feature Learning for Networks. A. Grover, J. Leskovec. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2016. ([link](https://snap.stanford.edu/node2vec/))\n", "\n", "[2] Distributed representations of words and phrases and their compositionality. T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. In Advances in Neural Information Processing Systems (NIPS), pp. 3111-3119, 2013. ([link](https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf))\n", "\n", "[3] word2vec Parameter Learning Explained. X. Rong. arXiv preprint arXiv:1411.2738. 2014 Nov 11. ([link](https://arxiv.org/pdf/1411.2738.pdf))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Introduction\n", "Following word2vec [2,3], for each (``target``,``context``) node pair $(v_i,v_j)$ collected from random walks, we learn the representation for the target node $v_i$ by using it to predict the existence of context node $v_j$, with the following three-layer neural network." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "![](word2vec-illustration.png)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Node $v_i$'s representation in the hidden layer is obtained by multiplying $v_i$'s one-hot representation in the input layer with the input-to-hidden weight matrix $W_{in}$, which is equivalent to look up the $i$th row of input-to-hidden weight matrix $W_{in}$. The existence probability of each node conditioned on node $v_i$ is outputted in the output layer, which is obtained by multiplying $v_i$'s hidden-layer representation with the hidden-to-out weight matrix $W_{out}$ followed by a softmax activation. To capture the ``target-context`` relation between $v_i$ and $v_j$, we need to maximize the probability $\\mathrm{P}(v_j|v_i)$. However, computing $\\mathrm{P}(v_j|v_i)$ is time consuming, which involves the matrix multiplication between $v_i$'s hidden-layer representation and the hidden-to-out weight matrix $W_{out}$. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To speed up the computing, we adopt the negative sampling strategy [2,3]. For each (``target``, ``context``) node pair, we sample a negative node $v_k$, which is not $v_i$'s context. To obtain the output, instead of multiplying $v_i$'s hidden-layer representation with the hidden-to-out weight matrix $W_{out}$ followed by a softmax activation, we only calculate the dot product between $v_i$'s hidden-layer representation and the $j$th column as well as the $k$th column of the hidden-to-output weight matrix $W_{out}$ followed by a sigmoid activation respectively. According to [3], the original objective to maximize $\\mathrm{P}(v_j|v_i)$ can be approximated by minimizing the cross entropy between $v_j$ and $v_k$'s outputs and their ground-truth labels (1 for $v_j$ and 0 for $v_k$)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Following [2,3], we denote the rows of the input-to-hidden weight matrix $W_{in}$ as ``input_embeddings`` and the columns of the hidden-to-out weight matrix $W_{out}$ as ``output_embeddings``. To build the Node2Vec model, we need look up ``input_embeddings`` for target nodes and ``output_embeddings`` for context nodes and calculate their inner product together with a sigmoid activation." ] }, { "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]==1.1.0" ] }, { "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(\"1.1.0\")\n", "except AttributeError:\n", " raise ValueError(\n", " f\"This notebook requires StellarGraph version 1.1.0, but a different version {sg.__version__} is installed. Please see .\"\n", " ) from None" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "\n", "from sklearn.manifold import TSNE\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.linear_model import LogisticRegressionCV\n", "from sklearn.metrics import accuracy_score\n", "\n", "import os\n", "import networkx as nx\n", "import numpy as np\n", "import pandas as pd\n", "from tensorflow import keras\n", "\n", "from stellargraph import StellarGraph\n", "from stellargraph.data import BiasedRandomWalk\n", "from stellargraph.data import UnsupervisedSampler\n", "from stellargraph.data import BiasedRandomWalk\n", "from stellargraph.mapper import Node2VecLinkGenerator, Node2VecNodeGenerator\n", "from stellargraph.layer import Node2Vec, link_classification\n", "\n", "from stellargraph import datasets\n", "from IPython.display import display, HTML\n", "\n", "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Dataset\n", "\n", "\n", "For clarity, we use only the largest connected component, ignoring isolated nodes and subgraphs; having these in the data does not prevent the algorithm from running and producing valid results." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "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, subjects = dataset.load(largest_connected_component_only=True)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "StellarGraph: Undirected multigraph\n", " Nodes: 2485, Edges: 5209\n", "\n", " Node types:\n", " paper: [2485]\n", " Features: float32 vector, length 1433\n", " Edge types: paper-cites->paper\n", "\n", " Edge types:\n", " paper-cites->paper: [5209]\n", " Weights: all 1 (default)\n" ] } ], "source": [ "print(G.info())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### The Node2Vec algorithm\n", "\n", "The Node2Vec algorithm introduced in [[1]](#refs) is a 2-step representation learning algorithm. The two steps are:\n", "\n", "1. Use random walks to generate sentences from a graph. A sentence is a list of node ids. The set of all sentences makes a corpus.\n", "\n", "2. The corpus is then used to learn an embedding vector for each node in the graph. Each node id is considered a unique word/token in a dictionary that has size equal to the number of nodes in the graph. The Word2Vec algorithm [[2]](#refs) is used for calculating the embedding vectors.\n", "\n", "In this implementation, we train the Node2Vec algorithm in the following two steps:\n", "\n", "1. Generate a set of (`target`, `context`) node pairs through starting the biased random walk with a fixed length at per node. The starting nodes are taken as the target nodes and the following nodes in biased random walks are taken as context nodes. For each (`target`, `context`) node pair, we generate 1 negative node pair.\n", "\n", "2. Train the Node2Vec algorithm through minimizing cross-entropy loss for `target-context` pair prediction, with the predictive value obtained by performing the dot product of the 'input embedding' of the target node and the 'output embedding' of the context node, followed by a sigmoid activation." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Specify the optional parameter values: the number of walks to take per node, the length of each walk. Here, to guarantee the running efficiency, we respectively set `walk_number` and `walk_length` to 100 and 5. Larger values can be set to them to achieve better performance." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "tags": [ "parameters" ] }, "outputs": [], "source": [ "walk_number = 100\n", "walk_length = 5" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create the biased random walker to perform context node sampling, with the specified parameters." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "walker = BiasedRandomWalk(\n", " G,\n", " n=walk_number,\n", " length=walk_length,\n", " p=0.5, # defines probability, 1/p, of returning to source node\n", " q=2.0, # defines probability, 1/q, for moving to a node away from the source node\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create the UnsupervisedSampler instance with the biased random walker." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "unsupervised_samples = UnsupervisedSampler(G, nodes=list(G.nodes()), walker=walker)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Set the batch size and the number of epochs." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "batch_size = 50\n", "epochs = 2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Define an attri2vec training generator, which generates a batch of (index of target node, index of context node, label of node pair) pairs per iteration." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "generator = Node2VecLinkGenerator(G, batch_size)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Build the Node2Vec model, with the dimension of learned node representations set to 128." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "emb_size = 128\n", "node2vec = Node2Vec(emb_size, generator=generator)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "x_inp, x_out = node2vec.in_out_tensors()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Use the link_classification function to generate the prediction, with the 'dot' edge embedding generation method and the 'sigmoid' activation, which actually performs the dot product of the 'input embedding' of the target node and the 'output embedding' of the context node followed by a sigmoid activation." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "link_classification: using 'dot' method to combine node embeddings into edge embeddings\n" ] } ], "source": [ "prediction = link_classification(\n", " output_dim=1, output_act=\"sigmoid\", edge_embedding_method=\"dot\"\n", ")(x_out)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Stack the Node2Vec encoder and prediction layer into a Keras model. Our generator will produce batches of positive and negative context pairs as inputs to the model. Minimizing the binary crossentropy between the outputs and the provided ground truth is much like a regular binary classification task." ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "model = keras.Model(inputs=x_inp, outputs=prediction)\n", "\n", "model.compile(\n", " optimizer=keras.optimizers.Adam(lr=1e-3),\n", " loss=keras.losses.binary_crossentropy,\n", " metrics=[keras.metrics.binary_accuracy],\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Train the model." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Train for 39760 steps\n", "Epoch 1/2\n", "39760/39760 [==============================] - 159s 4ms/step - loss: 0.2956 - binary_accuracy: 0.8537\n", "Epoch 2/2\n", "39760/39760 [==============================] - 193s 5ms/step - loss: 0.1089 - binary_accuracy: 0.9644\n" ] } ], "source": [ "history = model.fit(\n", " generator.flow(unsupervised_samples),\n", " epochs=epochs,\n", " verbose=1,\n", " use_multiprocessing=False,\n", " workers=4,\n", " shuffle=True,\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Visualise Node Embeddings" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Build the node based model for predicting node representations from node ids and the learned parameters. Below a Keras model is constructed, with x_inp[0] as input and x_out[0] as output. Note that this model's weights are the same as those of the corresponding node encoder in the previously trained node pair classifier." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "x_inp_src = x_inp[0]\n", "x_out_src = x_out[0]\n", "embedding_model = keras.Model(inputs=x_inp_src, outputs=x_out_src)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Get the node embeddings from node ids." ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "50/50 [==============================] - 0s 1ms/step\n" ] } ], "source": [ "node_gen = Node2VecNodeGenerator(G, batch_size).flow(G.nodes())\n", "node_embeddings = embedding_model.predict(node_gen, workers=4, verbose=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Transform the embeddings to 2d space for visualisation." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "transform = TSNE # PCA\n", "\n", "trans = transform(n_components=2)\n", "node_embeddings_2d = trans.fit_transform(node_embeddings)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# draw the embedding points, coloring them by the target label (paper subject)\n", "alpha = 0.7\n", "label_map = {l: i for i, l in enumerate(np.unique(subjects))}\n", "node_colours = [label_map[target] for target in subjects]\n", "\n", "plt.figure(figsize=(7, 7))\n", "plt.axes().set(aspect=\"equal\")\n", "plt.scatter(\n", " node_embeddings_2d[:, 0],\n", " node_embeddings_2d[:, 1],\n", " c=node_colours,\n", " cmap=\"jet\",\n", " alpha=alpha,\n", ")\n", "plt.title(\"{} visualization of node embeddings\".format(transform.__name__))\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Node Classification\n", "In this task, we will use the `Node2Vec` node embeddings to train a classifier to predict the subject of a paper in Cora." ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "# X will hold the 128-dimensional input features\n", "X = node_embeddings\n", "# y holds the corresponding target values\n", "y = np.array(subjects)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Data Splitting\n", "\n", "We split the data into train and test sets. \n", "\n", "We use 10% of the data for training and the remaining 90% for testing as a hold-out test set." ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Array shapes:\n", " X_train = (248, 128)\n", " y_train = (248,)\n", " X_test = (2237, 128)\n", " y_test = (2237,)\n" ] } ], "source": [ "X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.1, test_size=None)\n", "print(\n", " \"Array shapes:\\n X_train = {}\\n y_train = {}\\n X_test = {}\\n y_test = {}\".format(\n", " X_train.shape, y_train.shape, X_test.shape, y_test.shape\n", " )\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Classifier Training\n", "\n", "We train a Logistic Regression classifier on the training data. " ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "LogisticRegressionCV(Cs=10, class_weight=None, cv=10, dual=False,\n", " fit_intercept=True, intercept_scaling=1.0, l1_ratios=None,\n", " max_iter=300, multi_class='ovr', n_jobs=None, penalty='l2',\n", " random_state=None, refit=True, scoring='accuracy',\n", " solver='lbfgs', tol=0.0001, verbose=False)" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf = LogisticRegressionCV(\n", " Cs=10, cv=10, scoring=\"accuracy\", verbose=False, multi_class=\"ovr\", max_iter=300\n", ")\n", "clf.fit(X_train, y_train)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Predict the hold-out test set." ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "y_pred = clf.predict(X_test)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Calculate the accuracy of the classifier on the test set." ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7130084935181046" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "accuracy_score(y_test, y_pred)" ] }, { "cell_type": "markdown", "metadata": { "nbsphinx": "hidden", "tags": [ "CloudRunner" ] }, "source": [ "
Run the latest release of this notebook:
" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.6" } }, "nbformat": 4, "nbformat_minor": 2 }