@@ -8,17 +8,15 @@
 [![Documentation Status](https://readthedocs.org/projects/deephypergraph/badge/?version=latest)](https://deephypergraph.readthedocs.io/en/latest/?badge=latest)
 [![PyPI downloads](https://img.shields.io/pypi/dm/dhg.svg)](https://pypistats.org/packages/dhg)
 [![Visits Badge](https://visitor-badge.glitch.me/badge?page_id=iMoonLab.DeepHypergraph)](https://visitor-badge.glitch.me/)
-[![Code style: Black](https://img.shields.io/badge/code%20style-Black-000000.svg)](https://github.com/psf/black)
+<!-- [![Code style: Black](https://img.shields.io/badge/code%20style-Black-000000.svg)](https://github.com/psf/black) -->
 [![license](https://img.shields.io/github/license/imoonlab/DeepHypergraph)](LICENSE)
-[![Supported Python versions](https://img.shields.io/pypi/pyversions/dhg)](https://pypi.org/project/dhg/)
+<!-- [![Supported Python versions](https://img.shields.io/pypi/pyversions/dhg)](https://pypi.org/project/dhg/) -->
 
 
-**[Website](https://deephypergraph.com/)** | **[Documentation](https://deephypergraph.readthedocs.io/)** | **[Tutorials](https://deephypergraph.readthedocs.io/en/latest/tutorial/overview.html)** | **[中文教程](https://deephypergraph.readthedocs.io/en/latest/zh/overview.html)** | **[Official Examples](https://deephypergraph.readthedocs.io/en/latest/examples/vertex_cls/index.html)** | **[Discussions](https://github.com/iMoonLab/DeepHypergraph/discussions)**
+**[Website](https://deephypergraph.com/)** | **[Documentation](https://deephypergraph.readthedocs.io/)** | **[Tutorials](https://deephypergraph.readthedocs.io/en/latest/tutorial/overview.html)** | **[中文文档](https://deephypergraph.readthedocs.io/en/latest/zh/overview.html)** | **[Official Examples](https://deephypergraph.readthedocs.io/en/latest/examples/vertex_cls/index.html)** | **[Discussions](https://github.com/iMoonLab/DeepHypergraph/discussions)**
 
 <p align="center">
-We are rushing the documentation and tutorials, which will be updated twice a day!<br>
 The v0.9.2 will be released soon, which will include many structure visualizations!<br>
-我们正在加快文档和教程的更新，每天会在午饭和晚饭期间进行两次更新！<br>
 我们很快将发布v0.9.2版本，其中包含了各种关联结构的可视化！
 </p>
 
@@ -29,7 +27,7 @@ The v0.9.2 will be released soon, which will include many structure visualizatio
 
 **DHG** *(DeepHypergraph)* is a deep learning library built upon [PyTorch](https://pytorch.org) for learning with both Graph Neural Networks and Hypergraph Neural Networks. It is a general framework that supports both low-order and high-order message passing like **from vertex to vertex**, **from vertex in one domain to vertex in another domain**, **from vertex to hyperedge**, **from hyperedge to vertex**, **from vertex set to vertex set**.
 
-It supports a wide variety of structures like low-order structures (simple graph, directed graph, bipartite graph, etc.), high-order structures (simple hypergraph, etc.). Various spectral-based operations (like Laplacian-based smoothing) and spatial-based operations (like message psssing from domain to domain) are integrated inside different structures. It provides multiple common metrics for performance evaluation on different tasks. Many state-of-the-art models are implemented and can be easily used for research. We also provide various visualization tools for both low-order structures and high-order structures. 
+It supports a wide variety of structures like low-order structures (graph, directed graph, bipartite graph, etc.), high-order structures (hypergraph, etc.). Various spectral-based operations (like Laplacian-based smoothing) and spatial-based operations (like message psssing from domain to domain) are integrated inside different structures. It provides multiple common metrics for performance evaluation on different tasks. Many state-of-the-art models are implemented and can be easily used for research. We also provide various visualization tools for both low-order structures and high-order structures. 
 
 In addition, DHG's [dhg.experiments](https://deephypergraph.readthedocs.io/en/latest/api/experiments.html) module (that implements **Auto-ML** upon [Optuna](https://optuna.org)) can help you automatically tune the hyper-parameters of your models in training and easily outperforms the state-of-the-art models.
 
@@ -56,10 +54,10 @@ DHG is built upon Pytorch, and any Pytorch-based models can be integrated into D
 DHG provides various Laplacian matrices and message passing functions to help build your spectral/spatial-based models, respectively.
 
 - **Visualization of Graphs and Hypergraphs**
-DHG provides a powerful visualization tool for graphs and hypergraphs. You can easily visualize the structure of your graphs and hypergraphs.
+DHG provides a powerful visualization tool for graph and hypergraph. You can easily visualize the structure of your graph and hypergraph.
 
 - **Bridge the Gap between Graphs and Hypergraphs**:
-DHG provides functions to build hypergraphs from graphs and build graphs from hypergraphs. Maybe promoting the graphs to hypergraphs can exploit those potential high-order connections and improve the performance of your model.
+DHG provides functions to build hypergraph from graph and build graph from hypergraph. Maybe promoting the graph to hypergraph can exploit those potential high-order connections and improve the performance of your model.
 
 - **Attach Spectral/Spatial-Based Operations to Structure**:
 In DHG, those Laplacian matrices and message passing functions are attached to the graph/hypergraph structure. As soon as you build a structure with DHG, those functions will be ready to be used in the process of building your model.
@@ -84,7 +82,7 @@ pip install dhg
 
 ### Learning on Low-Order Structures
 
-On simple graph structures, you can smooth a given vertex features with GCN's Laplacian matrix by:
+On graph structures, you can smooth a given vertex features with GCN's Laplacian matrix by:
 
 ```python
 import torch
@@ -94,7 +92,7 @@ X = torch.rand(5, 2)
 X_ = g.smoothing_with_GCN(X)
 ```
 
-On simple graph structures, you can pass messages from vertex to vertex with `mean` aggregation by:
+On graph structures, you can pass messages from vertex to vertex with `mean` aggregation by:
 
 ```python
 import torch
@@ -138,7 +136,7 @@ X_v_ = g.u2v(X_u, aggr="mean")
 
 ### Learning on High-Order Structures
 
-On simple hypergraph structures, you can smooth a given vertex features with HGNN's Laplacian matrix by:
+On hypergraph structures, you can smooth a given vertex features with HGNN's Laplacian matrix by:
 
 ```python
 import torch
@@ -148,7 +146,7 @@ X = torch.rand(5, 2)
 X_ = hg.smoothing_with_HGNN(X)
 ```
 
-On simple hypergraph structures, you can pass messages from vertex to hyperedge with `mean` aggregation by:
+On hypergraph structures, you can pass messages from vertex to hyperedge with `mean` aggregation by:
 
 ```python
 import torch
@@ -362,7 +360,7 @@ If you find **DHG** is useful in your research, please consider citing:
 
 ## The DHG Team
 
-DHG is developed by DHG's core team including [Yifan Feng](http://fengyifan.site/), [Xinwei Zhang](https://github.com/zhangxwww), and [Yue Gao (Adivsor)](http://moon-lab.tech/). It is maintained by the [iMoon-Lab](http://moon-lab.tech/), Tsinghua University. You can contact us at [email](mailto:evanfeng97@gmail.com).
+DHG is developed by DHG's core team including [Yifan Feng](http://fengyifan.site/), [Xinwei Zhang](https://github.com/zhangxwww), [Jielong Yan](https://github.com/JasonYanjl), [Shuyi Ji](), [Yue Gao](http://moon-lab.tech/), and [Qionghai Dai](https://ysg.ckcest.cn/html/details/8058/index.html). It is maintained by the [iMoon-Lab](http://moon-lab.tech/), Tsinghua University. You can contact us at [email](mailto:evanfeng97@gmail.com).
 
 
 ## License
 
@@ -10,7 +10,7 @@
 
 
 class GraphVertexClassificationTask(VertexClassificationTask):
-    r"""The auto-experiment class for the vertex classification task on graphs.
+    r"""The auto-experiment class for the vertex classification task on graph.
 
     Args:
         ``work_root`` (``Optional[Union[str, Path]]``): User's work root to store all studies.
@@ -55,7 +55,7 @@ def to(self, device: torch.device):
 
     @property
     def vars_for_DL(self):
-        r"""Return a name list for available variables for deep learning in the vertex classification on graphs. The name list includes ``features``, ``structure``, ``labels``, ``train_mask``, ``val_mask``, and ``test_mask``.
+        r"""Return a name list for available variables for deep learning in the vertex classification on graph. The name list includes ``features``, ``structure``, ``labels``, ``train_mask``, ``val_mask``, and ``test_mask``.
         """
         return super().vars_for_DL
 
 
@@ -10,7 +10,7 @@
 
 
 class HypergraphVertexClassificationTask(VertexClassificationTask):
-    r"""The auto-experiment class for the vertex classification task on hypergraphs.
+    r"""The auto-experiment class for the vertex classification task on hypergraph.
 
     Args:
         ``work_root`` (``Optional[Union[str, Path]]``): User's work root to store all studies.
@@ -58,7 +58,7 @@ def to(self, device: torch.device):
 
     @property
     def vars_for_DL(self):
-        r"""Return a name list for available variables for deep learning in the vertex classification on hypergraphs. The name list includes ``features``, ``structure``, ``labels``, ``train_mask``, ``val_mask``, and ``test_mask``.
+        r"""Return a name list for available variables for deep learning in the vertex classification on hypergraph. The name list includes ``features``, ``structure``, ``labels``, ``train_mask``, ``val_mask``, and ``test_mask``.
         """
         return super().vars_for_DL
 
 
@@ -10,7 +10,7 @@
 
 
 class UserItemRecommenderTask(BaseTask):
-    r"""The auto-experiment class for the recommender task on user-item bipartite graphs.
+    r"""The auto-experiment class for the recommender task on user-item bipartite graph.
 
     Args:
         ``work_root`` (``Optional[Union[str, Path]]``): User's work root to store all studies.
@@ -63,7 +63,7 @@ def to(self, device: torch.device):
 
     @property
     def vars_for_DL(self):
-        r"""Return a name list for available deep learning variables for the recommender task on user-item bipartite graphs. The name list includes ``structure``.
+        r"""Return a name list for available deep learning variables for the recommender task on user-item bipartite graph. The name list includes ``structure``.
         """
         return ("structure",)
 
 
@@ -166,7 +166,7 @@ def ndcg(
 
 
 class UserItemRecommenderEvaluator(BaseEvaluator):
-    r"""Return the metric evaluator for recommender task on user-item bipartite graphs. The supported metrics includes: ``precision``, ``recall``, ``ndcg``.
+    r"""Return the metric evaluator for recommender task on user-item bipartite graph. The supported metrics includes: ``precision``, ``recall``, ``ndcg``.
     
     Args:
         ``metric_configs`` (``List[Union[str, Dict[str, dict]]]``): The metric configurations. The key is the metric name and the value is the metric parameters.
 
@@ -154,7 +154,7 @@ def from_adj_list(num_v: int, adj_list: List[List[int]], extra_selfloop: bool =
         r"""Construct a graph from the adjacency list. Each line in the adjacency list has two components. The first element in each line is the source vertex index, and the rest elements are the target vertex indices that connected to the source vertex.
 
         .. note::
-            This function can only construct unweighted graphs.
+            This function can only construct unweighted graph.
 
         Args:
             ``num_v`` (``int``): The number of vertices.
 
@@ -12,7 +12,7 @@
 
 
 class BiGraph(BaseGraph):
-    r""" Class for bipartite graphs.
+    r""" Class for bipartite graph.
 
         Args:
             ``num_u`` (``int``): The Number of vertices in set :math:`\mathcal{U}`.
 
@@ -12,7 +12,7 @@
 
 
 class DiGraph(BaseGraph):
-    r""" Class for directed graphs.
+    r""" Class for directed graph.
 
         Args:
             ``num_v`` (``int``): The Number of vertices.
 
@@ -13,7 +13,7 @@
 
 
 class Graph(BaseGraph):
-    r""" Class for simple graphs (undirected graphs).
+    r""" Class for graph (undirected graph).
 
         Args:
             ``num_v`` (``int``): The number of vertices.
@@ -40,11 +40,11 @@ def __init__(
     def __repr__(self) -> str:
         r"""Print the graph information.
         """
-        return f"Simple Graph(num_v={self.num_v}, num_e={self.num_e})"
+        return f"Graph(num_v={self.num_v}, num_e={self.num_e})"
 
     @property
     def state_dict(self) -> Dict[str, Any]:
-        r"""Get the state dict of the simple graph.
+        r"""Get the state dict of the graph.
         """
         return {
             "num_v": self.num_v,
@@ -111,7 +111,7 @@ def draw(
         pull_e_strength: float = 1.0,
         pull_center_strength: float = 1.0,
     ):
-        r"""Draw the simple graph structure. The supported edge styles are: ``'line'`` and ``'circle'``.
+        r"""Draw the graph structure. The supported edge styles are: ``'line'`` and ``'circle'``.
 
         Args:
             ``e_style`` (``str``): The edge style. The supported edge styles are: ``'line'`` and ``'circle'``. Defaults to ``'line'``.
@@ -151,7 +151,7 @@ def to(self, device: torch.device):
         r"""Move the graph to the specified device.
 
         Args:
-            ``device`` (``torch.device``): The device to store the simple graph.
+            ``device`` (``torch.device``): The device to store the graph.
         """
         return super().to(device)
 
@@ -167,7 +167,7 @@ def from_adj_list(
         r"""Construct a graph from the adjacency list. Each line in the adjacency list has two components. The first element in each line is the source vertex index, and the rest elements are the target vertex indices that connected to the source vertex.
 
         .. note::
-            This function can only construct the unweighted simple graph.
+            This function can only construct the unweighted graph.
 
         Args:
             ``num_v`` (``int``): The number of vertices.
@@ -344,7 +344,7 @@ def v(self) -> List[int]:
 
     @property
     def e(self) -> Tuple[List[List[int]], List[float]]:
-        r"""Return the edge list and weight list in the simple graph.
+        r"""Return the edge list and weight list in the graph.
         """
         return super().e
 
@@ -361,19 +361,19 @@ def e_both_side(self) -> Tuple[List[List], List[float]]:
 
     @property
     def num_v(self) -> int:
-        r"""Return the number of vertices in the simple graph.
+        r"""Return the number of vertices in the graph.
         """
         return super().num_v
 
     @property
     def num_e(self) -> int:
-        r"""Return the number of edges in the simple graph.
+        r"""Return the number of edges in the graph.
         """
         return super().num_e
 
     @property
     def deg_v(self) -> List[int]:
-        r"""Return the degree list of each vertex in the simple graph.
+        r"""Return the degree list of each vertex in the graph.
         """
         return self.D_v._values().cpu().numpy().tolist()
 
@@ -389,7 +389,7 @@ def nbr_v(self, v_idx: int) -> Tuple[List[int], List[float]]:
     # properties for deep learning
     @property
     def vars_for_DL(self) -> List[str]:
-        r"""Return a name list of available variables for deep learning in the simple graph including 
+        r"""Return a name list of available variables for deep learning in the graph including 
 
         Sparse Matrices: