update doc

README.md

@@ -86,7 +86,7 @@ Please make sure you meet the following requirements before installing AutoGL.
 
 3. Graph Library Backend
 
-You will need either PyTorch Geometric (PyG) or Deep Graph Library (DGL) as the backend. You can select a backend following [here](TODO) if you install both.
+    You will need either PyTorch Geometric (PyG) or Deep Graph Library (DGL) as the backend. You can select a backend following [here](TODO) if you install both.
 
 3.1 PyTorch Geometric (>=1.7.0)
 

autogl/module/feature/_generators/_eigen.py

@@ -60,7 +60,7 @@ class EigenFeatureGenerator(BaseFeatureGenerator):
     References
     ----------
     .. [#] Ziwei Zhang, Peng Cui, Jian Pei, Xin Wang, Wenwu Zhu:
-        Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs. CoRR abs/2006.04330 (2020)
+        Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs. TKDE (2021)
         https://arxiv.org/abs/2006.04330
 
 

docs/index.rst

@@ -13,7 +13,7 @@ The workflow below shows the overall framework of AutoGL.
 .. image:: ../resources/workflow.svg
    :align: center
 
-AutoGL uses ``AutoGL Dataset`` to maintain datasets for graph-based machine learning, which is based on the dataset in PyTorch Geometric with some support added to corporate with the auto solver framework.
+AutoGL uses ``AutoGL Dataset`` to maintain datasets for graph-based machine learning, which is based on the dataset in PyTorch Geometric or Deep Graph Library with some support added to corporate with the auto solver framework.
 
 Different graph-based machine learning tasks are solved by different ``AutoGL Solvers`` , which make use of four main modules to automatically solve given tasks, namely ``Auto Feature Engineer``, ``Auto Model``, ``Neural Architecture Search``, ``HyperParameter Optimization``, and ``Auto Ensemble``. 
 
@@ -31,17 +31,17 @@ Please make sure you meet the following requirements before installing AutoGL.
 
     see `PyTorch <https://pytorch.org/>`_ for installation.
 
-If you want to use Pytorch Geometric backend, you need to install:
+3. Graph Library Backend
 
-3. PyTorch Geometric (>=1.7.0)
+    You will need either PyTorch Geometric (PyG) or Deep Graph Library (DGL) as the backend.
 
-    see `PyTorch Geometric <https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html>`_ for installation.
+3.1 PyTorch Geometric (>=1.7.0)
 
-If you want to use Deep Graph Library backend, you need to install:
+    see <https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html> for installation.
 
-3. Deep Graph Library (>=0.7)
+3.2 Deep Graph Library (>=0.7.0)
 
-    see `Deep Graph Library <https://docs.dgl.ai/install/index.html>`_ for installation.
+    see <https://dgl.ai> for installation.
 
 Installation
 ~~~~~~~~~~~~
@@ -97,8 +97,11 @@ In AutoGL, the tasks are solved by corresponding solvers, which in general do th
    docfile/tutorial/t_hetero_node_clf
    docfile/tutorial/t_homo_graph_classification_gin
    docfile/tutorial/t_backend
-   docfile/tutorial/t_dataset
-   docfile/tutorial/t_fe
+
+   ..
+      docfile/tutorial/t_dataset
+      docfile/tutorial/t_fe
+   
    docfile/tutorial/t_model
    docfile/tutorial/t_trainer
    docfile/tutorial/t_hpo
@@ -111,8 +114,11 @@ In AutoGL, the tasks are solved by corresponding solvers, which in general do th
    :caption: Documentation
 
    docfile/documentation/data
-   docfile/documentation/dataset
-   docfile/documentation/feature
+   
+   ..
+      docfile/documentation/dataset
+      docfile/documentation/feature
+      
    docfile/documentation/model
    docfile/documentation/train
    docfile/documentation/hpo

docs/requirements.txt

@@ -13,11 +13,5 @@ requests
 scikit-learn
 scipy
 tabulate
-# https://download.pytorch.org/whl/lts/1.8/cpu/torch-1.8.1%2Bcpu-cp36-cp36m-linux_x86_64.whl
-# https://pytorch-geometric.com/whl/torch-1.8.0+cpu/torch_cluster-1.5.9-cp36-cp36m-linux_x86_64.whl
-# https://pytorch-geometric.com/whl/torch-1.8.0+cpu/torch_scatter-2.0.6-cp36-cp36m-linux_x86_64.whl
-# https://pytorch-geometric.com/whl/torch-1.8.0+cpu/torch_sparse-0.6.10-cp36-cp36m-linux_x86_64.whl
-# https://pytorch-geometric.com/whl/torch-1.8.0+cpu/torch_spline_conv-1.2.1-cp36-cp36m-linux_x86_64.whl
-# torch-geometric
 tqdm
 nni

setup.py

@@ -16,7 +16,7 @@ with open("README.md", 'r') as fh:
 ''' https://setuptools.readthedocs.io/en/latest/ '''
 setup(
     name='autogl',
-    version='0.2.0-pre',
+    version='0.3.0-pre',
     author='THUMNLab/aglteam',
     maintainer='THUMNLab/aglteam',
     author_email='autogl@tsinghua.edu.cn',