:orphan:

A Blitz Introduction to DGL
===========================



.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="GNNs are powerful tools for many machine learning tasks on graphs. In this introductory tutorial, you will learn the basic workflow of using GNNs for node classification, i.e. predicting the category of a node in a graph.">

.. only:: html

  .. image:: /tutorials/blitz/images/thumb/sphx_glr_1_introduction_thumb.png
    :alt:

  :ref:`sphx_glr_tutorials_blitz_1_introduction.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Node Classification with DGL</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="By the end of this tutorial you will be able to:">

.. only:: html

  .. image:: /tutorials/blitz/images/thumb/sphx_glr_2_dglgraph_thumb.png
    :alt:

  :ref:`sphx_glr_tutorials_blitz_2_dglgraph.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">How Does DGL Represent A Graph?</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Sometimes, your model goes beyond simply stacking existing GNN modules. For example, you would like to invent a new way of aggregating neighbor information by considering node importance or edge weights.">

.. only:: html

  .. image:: /tutorials/blitz/images/thumb/sphx_glr_3_message_passing_thumb.png
    :alt:

  :ref:`sphx_glr_tutorials_blitz_3_message_passing.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Write your own GNN module</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In the 1_introduction, you have already learned the basic workflow of using GNNs for node classification, i.e. predicting the category of a node in a graph. This tutorial will teach you how to train a GNN for link prediction, i.e. predicting the existence of an edge between two arbitrary nodes in a graph.">

.. only:: html

  .. image:: /tutorials/blitz/images/thumb/sphx_glr_4_link_predict_thumb.png
    :alt:

  :ref:`sphx_glr_tutorials_blitz_4_link_predict.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Link Prediction using Graph Neural Networks</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="By the end of this tutorial, you will be able to">

.. only:: html

  .. image:: /tutorials/blitz/images/thumb/sphx_glr_5_graph_classification_thumb.png
    :alt:

  :ref:`sphx_glr_tutorials_blitz_5_graph_classification.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Training a GNN for Graph Classification</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial assumes that you already know the basics of training a GNN for node classification &lt;1_introduction&gt; and how to create, load, and store a DGL graph &lt;2_dglgraph&gt;.">

.. only:: html

  .. image:: /tutorials/blitz/images/thumb/sphx_glr_6_load_data_thumb.png
    :alt:

  :ref:`sphx_glr_tutorials_blitz_6_load_data.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Make Your Own Dataset</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /tutorials/blitz/1_introduction
   /tutorials/blitz/2_dglgraph
   /tutorials/blitz/3_message_passing
   /tutorials/blitz/4_link_predict
   /tutorials/blitz/5_graph_classification
   /tutorials/blitz/6_load_data



.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_