Merge branch 'dev' into robustGNAS

docs/docfile/tutorial/t_robust.rst

@@ -1,27 +1,31 @@
 .. _robust:
 
-Robust Model
-============
-
-We provides a series of defense methods that aim to enhance the robustness of GNNs.
+Graph Robustness
+==========================
 
-Requirements
-------------
+Graph robustness is an important research direction in the field of graph representation learning in recent years, 
+and we have integrated graph robustness-related algorithms in AutoGL, which can be easily used in conjunction with other modules.
 
-During the evaluation, the adversarial attacks on graph are performed by DeepRobust from MSU, please install it by
+Preliminaries
+-----------
+In AutoGL, we divide the algorithms for graph robustness into three categories, which are placed in different modules for implementation.
+Robust graph feature engineering aims to generate robust graph features in the data pre-processing phase to enhance the robustness of downstream tasks.
+Robust graph neural networks, on the other hand, are designed at the model level to ensure the robustness of the model during the training process.
+Robust graph neural network architecture search aims to search for a robust graph neural network architecture.
+Each of these three types of graph robustness algorithms will be described in the following sections.
 
-.. code-block:: bash
+Robust Graph Feature Engineering
+-----------
 
-    git clone https://github.com/DSE-MSU/DeepRobust.git
-    cd DeepRobust
-    python setup.py install
+We provide structure engineering methods to enhance robustness, please refer to `preprocessing` part for more information.
 
-To better plugin GNNGuard to AutoGL, we slightly revised some functions in geometric. Please use the file ``AutoGL/autogl/module/model/pyg/robust/nn/conv/gcn_conv.py`` we provided to replace the corresponding file in the installed geometric folder (for example, the folder path could be `/home/username/.local/lib/python3.5/site-packages/torch_geometric/nn/conv/`).
+Robust Model
+-----------
 
-*Note:* Don't forget to backup all the original files when you replacing anything, in case you need them at other places!
+We provides a series of defense methods that aim to enhance the robustness of GNNs.
 
 Building GNNGuard Module
-------------------------
+>>>>>>>>>>>>>>>>>>>
 
 Firstly, load pre-attacked graph data:
 
@@ -81,7 +85,7 @@ Thirdly, train defense model GNNGuard on poinsed graph:
 
 Robust Graph Neural Architecture Search
 ---------------------------------------
-Robust Graph Neural Architecture Search aims to search for adversarial robust Graph Neural Networks under attack.
+Robust Graph Neural Architecture Search aims to search for adversarial robust Graph Neural Networks under attacks.
 In AutoGL, this module is the code realization of G-RNA. 
 
 Specifically, we design a robust search space for the message-passing mechanism by adding the adjacency mask operations into the search space, 
@@ -191,8 +195,6 @@ Next, search for best robust architecture.
     trainer = solver.graph_model_list[0]
     trainer.device = device
 
-
-
 After getting the best architecture, we could evaluate on clean/perturbed graph data.
 
 .. code-block:: python
@@ -233,4 +235,4 @@ After getting the best architecture, we could evaluate on clean/perturbed graph
     ## test searched model on perturbed data
     data = dataset[0].cpu()
     dataset[0] = metattack(data).to(device)
-    ptb_acc = test_from_data(trainer, dataset)
+    ptb_acc = test_from_data(trainer, dataset)

docs/docfile/tutorial_cn/t_robust.rst

@@ -1,12 +1,33 @@
-.. _robust:
+.. _robust_cn:
 
-鲁棒模型
-==========================
+图鲁棒性
+============================
+
+图鲁棒性是近年图机器学习领域重要的研究方向，我们在AutoGL中集成了图鲁棒性相关算法，可以方便地与其他模块结合使用。
+
+背景知识
+------------
+
+（介绍对抗攻击、鲁棒问题的定义等，可以适当引一些paper）
+
+在AutoGL中，我们将图鲁棒性的算法分为三类，放在不同的模块中实现。
+鲁棒图特征工程旨在数据预处理阶段生成鲁棒的图特征，增强下游任务的鲁棒性。
+鲁棒图神经网络则是通过模型层面的设计，以在训练过程中确保模型的鲁棒性。
+鲁棒图神经网络架构搜索旨在搜索出一个鲁棒的图神经网络架构。
+下文中将分别介绍这三类图鲁棒性算法。
+
+鲁棒图特征工程
+---------------------
+
+我们提供了图结构特征工程的系列方法来提高鲁棒性，请参考`预处理`部分获取更多信息。
+
+鲁棒图神经网络
+---------------------
 
 我们提供了一系列的防御方法，旨在增强图神经网络的鲁棒性。
 
 生成并训练 GNNGuard 模型
-------------------------------
+>>>>>>>>>>>>>>>>>>>
 
 首先，加载预先攻击的图数据：