From 8a4b4590af63e0cefddb9d6abe02a6239deba3f2 Mon Sep 17 00:00:00 2001 From: JiaxuanYou Date: Mon, 28 Jun 2021 17:12:31 -0700 Subject: [PATCH] update figure caption --- README.md | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 2374d4dc..37d938e4 100644 --- a/README.md +++ b/README.md @@ -37,8 +37,8 @@ Using existing packages for GNN, you still have to code up the essential pipelin GraphGym is a perfect place for your to start learning *standardized GNN implementation and evaluation*.
- -

Figure 1: Modularized GNN implementation.
+ +
Figure 1: Modularized GNN implementation.

@@ -51,10 +51,11 @@ GraphGym provides a *simple interface to try out thousands of GNNs in parallel* GraphGym also recommends a "go-to" GNN design space, after investigating 10 million GNN model-task combinations.
- -

Figure 2: A guideline for desirable GNN design choices.
(Sampling from 10 million GNN model-task combinations.)
+ +
Figure 2: A guideline for desirable GNN design choices.
(Sampling from 10 million GNN model-task combinations.)
+
@@ -67,10 +68,11 @@ Moreover, GraphGym can help you easily do hyper-parameter search, and *visualize In sum, GraphGym can greatly facilitate your GNN research.
- -

Figure 3: Evaluation of a given GNN design dimension (BatchNorm here).
+ +
Figure 3: Evaluation of a given GNN design dimension (BatchNorm here).
+
## Installation @@ -228,7 +230,7 @@ For example, the base file could specify an experiment of 3-layer GCN for Cora n Then, the grid file specifies how to perturb the experiment along different dimension, such as number of layers, model architecture, dataset, level of task, etc. - + **2.4 Generate config files for the batch of experiments,** based on the information specified above. For example, in [`run/run_batch.sh`](run/run_batch.sh): ```bash @@ -322,8 +324,8 @@ design_space.ipynb # reproducing all the analyses in the paper ```
- -

Figure 4: Overview of the proposed GNN design space and task space.
+ +
Figure 4: Overview of the proposed GNN design space and task space.
@@ -343,8 +345,8 @@ bash run_idgnn_graph.sh # Reproduce ID-GNN graph-level results ```
- -

Figure 5: Overview of Identity-aware Graph Neural Networks (ID-GNN).
+ +
Figure 5: Overview of Identity-aware Graph Neural Networks (ID-GNN).