diff --git a/README.md b/README.md
index fcb09c22c60defef53cc75451d977194d08b97da..3a58bf618ebcde862336f281b21ca5078dfb7ef0 100644
--- a/README.md
+++ b/README.md
@@ -63,8 +63,7 @@ If we use complex user-defined aggregation like [GraphSAGE-LSTM](https://cs.stan
 
 PGL requires:
 
-* paddle >= 1.5
-* networkx
+* paddle >= 1.6
 * cython
 
 
@@ -73,7 +72,7 @@ PGL supports both Python 2 & 3
 
 ## Installation
 
-The current version of PGL is 0.1.0.beta. You can simply install it via pip.
+The current version of PGL is 1.0.0. You can simply install it via pip.
 
 ```sh
 pip install pgl
diff --git a/README.zh.md b/README.zh.md
index aa6c92c195f0efac8092bf0cec75e69d15ab62e4..5af657c1e05f7ce5f52cfffe5edf1355cf96c163 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -58,8 +58,7 @@ Paddle Graph Learning (PGL)是一个基于[PaddlePaddle](https://github.com/Padd
 
 PGL依赖于:
 
-* paddle >= 1.5
-* networkx
+* paddle >= 1.6
 * cython
 
 
@@ -68,7 +67,7 @@ PGL支持Python 2和3。
 
 ## 安装
 
-当前，PGL的版本是0.1.0.beta。你可以简单的用pip进行安装。
+当前，PGL的版本是1.0.0。你可以简单的用pip进行安装。
 
 ```sh
 pip install pgl
@@ -81,4 +80,3 @@ PGL由百度的NLP以及Paddle团队共同开发以及维护。
 ## License
 
 PGL uses Apache License 2.0.
-
diff --git a/docs/requirements.txt b/docs/requirements.txt
index 4e7960b2517dee1e49324ec1245b1a49595126bc..8178df62d1c796588ce38714f1978efeea0b9875 100644
--- a/docs/requirements.txt
+++ b/docs/requirements.txt
@@ -3,5 +3,6 @@ mistune
 sphinx_rtd_theme
 numpy >= 1.16.4
 cython >= 0.25.2
+networkx
 paddlepaddle
 pgl
diff --git a/docs/source/conf.py b/docs/source/conf.py
index bfa66052064eaa1170023cb8a25278829deaff2f..ca7cb8eab16bc3817bcf23df78cfa2c9b68382f0 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -40,7 +40,7 @@ copyright = '2019, PaddlePaddle'
 author = 'PaddlePaddle'
 
 # The full version, including alpha/beta/rc tags
-release = '0.1.0.beta'
+release = '1.0.0'
 
 # -- General configuration ---------------------------------------------------
 
diff --git a/examples/dgi/README.md b/examples/dgi/README.md
index 3de5252e1ceb5482013cc8de224cc4080a5fab58..34481e06d4576c7969fe68c7a7b6a5f5e319d0c9 100644
--- a/examples/dgi/README.md
+++ b/examples/dgi/README.md
@@ -1,4 +1,4 @@
-# PGL Examples for GCN
+# PGL Examples for DGI
 
 [Deep Graph Infomax \(DGI\)](https://arxiv.org/abs/1809.10341) is a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures.