stellargraph/stellargraph

View on GitHub
demos/embeddings/node2vec-embeddings.ipynb

Summary

Maintainability
Test Coverage
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0",
   "metadata": {},
   "source": [
    "# Node representation learning with Node2Vec\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1",
   "metadata": {
    "nbsphinx": "hidden",
    "tags": [
     "CloudRunner"
    ]
   },
   "source": [
    "<table><tr><td>Run the latest release of this notebook:</td><td><a href=\"https://mybinder.org/v2/gh/stellargraph/stellargraph/master?urlpath=lab/tree/demos/embeddings/node2vec-embeddings.ipynb\" alt=\"Open In Binder\" target=\"_parent\"><img src=\"https://mybinder.org/badge_logo.svg\"/></a></td><td><a href=\"https://colab.research.google.com/github/stellargraph/stellargraph/blob/master/demos/embeddings/node2vec-embeddings.ipynb\" alt=\"Open In Colab\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\"/></a></td></tr></table>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2",
   "metadata": {},
   "source": [
    "An example of implementing the Node2Vec representation learning algorithm using components from the stellargraph and gensim libraries.\n",
    "\n",
    "<a name=\"refs\"></a>\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] Gensim: Topic modelling for humans. ([link](https://radimrehurek.com/gensim/))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3",
   "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]==1.3.0b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4",
   "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(\"1.3.0b\")\n",
    "except AttributeError:\n",
    "    raise ValueError(\n",
    "        f\"This notebook requires StellarGraph version 1.3.0b, but a different version {sg.__version__} is installed.  Please see <https://github.com/stellargraph/stellargraph/issues/1172>.\"\n",
    "    ) from None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from sklearn.manifold import TSNE\n",
    "from sklearn.decomposition import PCA\n",
    "import os\n",
    "import networkx as nx\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from stellargraph import datasets\n",
    "from IPython.display import display, HTML\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6",
   "metadata": {},
   "source": [
    "## Dataset\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": "markdown",
   "id": "7",
   "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,
   "id": "8",
   "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": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset = datasets.Cora()\n",
    "display(HTML(dataset.description))\n",
    "G, node_subjects = dataset.load(largest_connected_component_only=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "StellarGraph: Undirected multigraph\n",
      " Nodes: 2485, Edges: 5209\n",
      "\n",
      " Node types:\n",
      "  paper: [2485]\n",
      "    Edge types: paper-cites->paper\n",
      "\n",
      " Edge types:\n",
      "    paper-cites->paper: [5209]\n"
     ]
    }
   ],
   "source": [
    "print(G.info())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10",
   "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 second-order 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"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "11",
   "metadata": {},
   "source": [
    "## Corpus generation using random walks\n",
    "\n",
    "The stellargraph library provides an implementation for second-order random walks as required by Node2Vec. The random walks have fixed maximum length and are controlled by two parameters `p` and `q`. See [[1]](#refs) for a detailed description of these parameters. \n",
    "\n",
    "We are going to start 10 random walks from each node in the graph with a length up to 100. We set parameter `p` to 0.5 (which encourages backward steps) and `q` to 2.0 (which discourages distant steps); the net result is that walks should remain in the local vicinity of the starting nodes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "12",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of random walks: 24850\n"
     ]
    }
   ],
   "source": [
    "from stellargraph.data import BiasedRandomWalk\n",
    "\n",
    "rw = BiasedRandomWalk(G)\n",
    "\n",
    "walks = rw.run(\n",
    "    nodes=list(G.nodes()),  # root nodes\n",
    "    length=100,  # maximum length of a random walk\n",
    "    n=10,  # number of random walks per root node\n",
    "    p=0.5,  # Defines (unormalised) probability, 1/p, of returning to source node\n",
    "    q=2.0,  # Defines (unormalised) probability, 1/q, for moving away from source node\n",
    ")\n",
    "print(\"Number of random walks: {}\".format(len(walks)))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13",
   "metadata": {},
   "source": [
    "## Representation Learning using Word2Vec\n",
    "\n",
    "We use the Word2Vec [[2]](#refs) implementation in the free Python library gensim [[3]](#refs), to learn representations for each node in the graph. It works with `str` tokens, but the graph has integer IDs, so they're converted to `str` here.\n",
    "\n",
    "We set the dimensionality of the learned embedding vectors to 128 as in [[1]](#refs)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "14",
   "metadata": {},
   "outputs": [],
   "source": [
    "from gensim.models import Word2Vec\n",
    "\n",
    "str_walks = [[str(n) for n in walk] for walk in walks]\n",
    "model = Word2Vec(\n",
    "    str_walks, vector_size=128, window=5, min_count=0, sg=1, workers=2, epochs=1\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "15",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(128,)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# The embedding vectors can be retrieved from model.wv using the node ID.\n",
    "model.wv[\"19231\"].shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16",
   "metadata": {},
   "source": [
    "## Visualise Node Embeddings\n",
    "\n",
    "We retrieve the Word2Vec node embeddings that are 128-dimensional vectors and then we project them down to 2 dimensions using the [t-SNE](http://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html) algorithm."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "17",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Retrieve node embeddings and corresponding subjects\n",
    "node_ids = model.wv.index_to_key  # list of node IDs\n",
    "node_embeddings = (\n",
    "    model.wv.vectors\n",
    ")  # numpy.ndarray of size number of nodes times embeddings dimensionality\n",
    "node_targets = node_subjects.loc[[int(node_id) for node_id in node_ids]]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "18",
   "metadata": {},
   "source": [
    "Transform the embeddings to 2d space for visualisation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "19",
   "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": 11,
   "id": "20",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "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(node_targets))}\n",
    "node_colours = [label_map[target] for target in node_targets]\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",
   "id": "21",
   "metadata": {},
   "source": [
    "## Downstream task\n",
    "\n",
    "The node embeddings calculated using Word2Vec can be used as feature vectors in a downstream task such as node attribute inference (e.g., inferring the subject of a paper in Cora), community detection (clustering of nodes based on the similarity of their embedding vectors), and link prediction (e.g., prediction of citation links between papers).\n",
    "\n",
    "For a more detailed example of using Node2Vec for link prediction see [this example](../link-prediction/node2vec-link-prediction.ipynb)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "22",
   "metadata": {
    "nbsphinx": "hidden",
    "tags": [
     "CloudRunner"
    ]
   },
   "source": [
    "<table><tr><td>Run the latest release of this notebook:</td><td><a href=\"https://mybinder.org/v2/gh/stellargraph/stellargraph/master?urlpath=lab/tree/demos/embeddings/node2vec-embeddings.ipynb\" alt=\"Open In Binder\" target=\"_parent\"><img src=\"https://mybinder.org/badge_logo.svg\"/></a></td><td><a href=\"https://colab.research.google.com/github/stellargraph/stellargraph/blob/master/demos/embeddings/node2vec-embeddings.ipynb\" alt=\"Open In Colab\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\"/></a></td></tr></table>"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}