update some figures

Author: KiddoZhu

README.md

@@ -3,6 +3,8 @@
 ----------------------------
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1rutJkuYH3zaxBsMROWMvAu5LQCRcKcOg?usp=sharing#forceEdit=true&sandboxMode=true)
+[![Contributions](https://img.shields.io/badge/contributions-welcome-blue)](https://github.com/DeepGraphLearning/torchdrug/blob/master/CONTRIBUTING.md)
+[![License Apache-2.0](https://img.shields.io/github/license/DeepGraphLearning/torchdrug?color=blue)](https://github.com/DeepGraphLearning/torchdrug/blob/master/LICENSE)
 
 [Docs] | [Tutorials] | [Benchmarks] | [Papers Implemented]
 

asset/logo.svg

@@ -26,6 +26,11 @@ PackedMolecule
 .. autoclass:: PackedMolecule
     :members:
 
+Dictionary
+^^^^^^^^^^
+.. autoclass:: Dictionary
+    :members:
+
 Datasets
 --------
 .. currentmodule:: torchdrug.data

asset/graph/attrmasking.png renamed to asset/model/attribute_masking.png

@@ -135,10 +135,6 @@ MOSES
 .. autoclass:: MOSES
     :members:
 
-PCQM4M
-^^^^^^
-.. autoclass:: PCQM4M
-    :members:
 
 Retrosynthesis Datasets
 -----------------------
@@ -165,4 +161,4 @@ CiteSeer
 PubMed
 ^^^^^^
 .. autoclass:: PubMed
-    :members:
+    :members:

asset/graph/ContextPred.png renamed to asset/model/context_prediction.png

@@ -30,7 +30,7 @@ and node-level representations. It learns the model by distinguishing whether a
 node-graph pair comes from a single graph or two different graphs. The following
 figure illustrates the high-level idea of InfoGraph.
 
-.. image:: ../../../asset/graph/infograph.png
+.. image:: ../../../asset/model/infograph.png
 
 We use GIN as our graph represenation model, and wrap it with InfoGraph.
 
@@ -71,7 +71,7 @@ The aim of `Attribute Masking`_ (AM) is to capture domain knowledge by learning
 regularities of the node/edge attributes distributed over graph structure. The high-level
 idea is to predict atom types in molecular graphs from randomly masked node features.
 
-.. image:: ../../../asset/graph/attrmasking.png
+.. image:: ../../../asset/model/attribute_masking.png
 
 Again, we use GIN as our graph representation model.