From 95cbb33996fd2db9c0763be22fee27b10f2aae70 Mon Sep 17 00:00:00 2001 From: Aurora Rossi <65721467+aurorarossi@users.noreply.github.com> Date: Tue, 24 Dec 2024 22:42:18 +0100 Subject: [PATCH 1/2] Fix Co-authored-by: Carlo Lucibello --- GNNLux/docs/src/tutorials/graph_classification.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/GNNLux/docs/src/tutorials/graph_classification.md b/GNNLux/docs/src/tutorials/graph_classification.md index 9eb3c2627..d2db19783 100644 --- a/GNNLux/docs/src/tutorials/graph_classification.md +++ b/GNNLux/docs/src/tutorials/graph_classification.md @@ -3,7 +3,7 @@ *This tutorial is a Julia adaptation of the Pytorch Geometric tutorial that can be found [here](https://pytorch-geometric.readthedocs.io/en/latest/notes/colabs.html).* In this tutorial session we will have a closer look at how to apply **Graph Neural Networks (GNNs) to the task of graph classification**. -Graph classification refers to the problem of classifying entire graphs (in contrast to nodes), given a **dataset of graphs**, based on some structural graph properties. +Graph classification refers to the problem of classifying entire graphs (in contrast to nodes), given a **dataset of graphs**, based on some structural graph properties and possibly on some input node features. Here, we want to embed entire graphs, and we want to embed those graphs in such a way so that they are linearly separable given a task at hand. The most common task for graph classification is **molecular property prediction**, in which molecules are represented as graphs, and the task may be to infer whether a molecule inhibits HIV virus replication or not. From d3f67374c451244dd2ad68666da63caaf9390414 Mon Sep 17 00:00:00 2001 From: Aurora Rossi <65721467+aurorarossi@users.noreply.github.com> Date: Tue, 24 Dec 2024 22:42:46 +0100 Subject: [PATCH 2/2] Fix text Co-authored-by: Carlo Lucibello --- GNNLux/docs/src/tutorials/graph_classification.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/GNNLux/docs/src/tutorials/graph_classification.md b/GNNLux/docs/src/tutorials/graph_classification.md index d2db19783..e9e2443d6 100644 --- a/GNNLux/docs/src/tutorials/graph_classification.md +++ b/GNNLux/docs/src/tutorials/graph_classification.md @@ -6,7 +6,7 @@ In this tutorial session we will have a closer look at how to apply **Graph Neur Graph classification refers to the problem of classifying entire graphs (in contrast to nodes), given a **dataset of graphs**, based on some structural graph properties and possibly on some input node features. Here, we want to embed entire graphs, and we want to embed those graphs in such a way so that they are linearly separable given a task at hand. -The most common task for graph classification is **molecular property prediction**, in which molecules are represented as graphs, and the task may be to infer whether a molecule inhibits HIV virus replication or not. +A common graph classification task is **molecular property prediction**, in which molecules are represented as graphs, and the task may be to infer whether a molecule inhibits HIV virus replication or not. The TU Dortmund University has collected a wide range of different graph classification datasets, known as the [**TUDatasets**](https://chrsmrrs.github.io/datasets/), which are also accessible via MLDatasets.jl. Let's import the necessary packages. Then we'll load and inspect one of the smaller ones, the **MUTAG dataset**: