{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n\nRelational Graph Convolutional Network\n================================================\n\n**Author:** Lingfan Yu, Mufei Li, Zheng Zhang\n\n
The tutorial aims at gaining insights into the paper, with code as a mean\n of explanation. The implementation thus is NOT optimized for running\n efficiency. For recommended implementation, please refer to the `official\n examples
Another weight regularization, block-decomposition, is implemented in\n the `link prediction
Each relation type is associated with a different weight. Therefore,\n the full weight matrix has three dimensions: relation, input_feature,\n output_feature.
This is showing how to implement an R-GCN from scratch. DGL provides a more\n efficient :class:`builtin R-GCN layer module