Add arxiv

.github/actions/setup/action.yaml

@@ -3,7 +3,7 @@ name: Setup
 inputs:
   python-version:
     required: false
-    default: '3.8'
+    default: '3.10'
   torch-version:
     required: false
     default: '2.3.0'

.github/workflows/docs.yaml

@@ -47,7 +47,7 @@ jobs:
       - name: Install main package
         if: steps.changed-files-specific.outputs.only_changed != 'true'
         run: |
-          pip install -e .[docs]
+          pip install -e .[docs,benchmark]
 
       - name: Enable github problem matcher
         uses: sphinx-doc/github-problem-matcher@master

CITATION.cff

@@ -0,0 +1,43 @@
+cff-version: 1.2.0
+message: "If you use this framework, please cite our paper as below."
+authors:
+  - family-names: Liao
+    given-names: Ningyi
+    orcid: https://orcid.org/0000-0003-3176-4401
+  - family-names: Liu
+    given-names: Haoyu
+  - family-names: Zhu
+    given-names: Zulun
+  - family-names: Luo
+    given-names: Siqiang
+    orcid: https://orcid.org/0000-0001-8197-0903
+  - family-names: Lakshmanan
+    given-names: Laks
+    orcid: https://orcid.org/0000-0002-9775-4241
+title: "pyg_spectral"
+version: 1.0.0
+date-released: 2024-05-28
+preferred-citation:
+  type: report
+  authors:
+  - family-names: Liao
+    given-names: Ningyi
+    orcid: https://orcid.org/0000-0003-3176-4401
+  - family-names: Liu
+    given-names: Haoyu
+  - family-names: Zhu
+    given-names: Zulun
+  - family-names: Luo
+    given-names: Siqiang
+    orcid: https://orcid.org/0000-0001-8197-0903
+  - family-names: Lakshmanan
+    given-names: Laks
+    orcid: https://orcid.org/0000-0002-9775-4241
+  journal: "arXiv e-prints"
+  month: 6
+  start: 1
+  end: 37
+  title: "Benchmarking Spectral Graph Neural Networks: A Comprehensive Study on Effectiveness and Efficiency"
+  issue: arXiv:2406.09675
+  year: 2024
+  eprint: 2406.09675

README.md

@@ -2,8 +2,8 @@
 
 [![Docs](https://github.com/gdmnl/Spectral-GNN-Benchmark/actions/workflows/docs.yaml/badge.svg)](https://gdmnl.github.io/Spectral-GNN-Benchmark/)
 [![LICENSE](https://img.shields.io/github/license/gdmnl/Spectral-GNN-Benchmark)](LICENSE)
-[![Release](https://img.shields.io/github/v/release/gdmnl/Spectral-GNN-Benchmark?include_prereleases)](https://github.com/gdmnl/Spectral-GNN-Benchmark/releases)
-[![Python](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Fgdmnl%2FSpectral-GNN-Benchmark%2Fmain%2Fpyproject.toml)]()
+[![Release](https://img.shields.io/github/v/release/gdmnl/Spectral-GNN-Benchmark?include_prereleases)](https://github.com/gdmnl/Spectral-GNN-Benchmark/releases/latest)
+[![Python](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Fgdmnl%2FSpectral-GNN-Benchmark%2Fmain%2Fpyproject.toml)](https://gdmnl.github.io/Spectral-GNN-Benchmark/installation.html#)
 
 `pyg_spectral` is a [PyTorch Geometric](https://pyg.org)-based framework for analyzing, implementing, and benchmarking spectral GNNs with effectiveness and efficiency evaluations.
 
@@ -16,7 +16,7 @@
 
 ---
 
-[**Documentation**](https://gdmnl.github.io/Spectral-GNN-Benchmark/) | [**GitHub**](https://github.com/gdmnl/Spectral-GNN-Benchmark/)
+[:mag: **Documentation**](https://gdmnl.github.io/Spectral-GNN-Benchmark/) | [:octocat: **GitHub**](https://github.com/gdmnl/Spectral-GNN-Benchmark/) | [:page_facing_up: **Paper**](https://arxiv.org/abs/2406.09675) | [:paperclip: **Cite**](CITATION.cff)
 
 - [Installation](#installation)
 - [Reproduce Experiments](#reproduce-experiments)
@@ -198,9 +198,9 @@ out = model(x, edge_index)
 
 | **Category** | **Model** |
 |:------------:|:----------|
-| Fixed Filter | [GCN](https://arxiv.org/abs/1609.02907), [SGC](https://arxiv.org/pdf/1902.07153), [gfNN](https://arxiv.org/pdf/1905.09550), [GZoom](https://arxiv.org/pdf/1910.02370), [S$^2$GC](https://openreview.net/pdf?id=CYO5T-YjWZV),[GLP](https://arxiv.org/pdf/1901.09993), [APPNP](https://arxiv.org/pdf/1810.05997), [GCNII](https://arxiv.org/pdf/2007.02133), [GDC](https://proceedings.neurips.cc/paper_files/paper/2019/file/23c894276a2c5a16470e6a31f4618d73-Paper.pdf), [DGC](https://arxiv.org/pdf/2102.10739), [AGP](https://arxiv.org/pdf/2106.03058), [GRAND+](https://arxiv.org/pdf/2203.06389)|
-|Variable Filter|[GIN](https://arxiv.org/pdf/1810.00826), [AKGNN](https://arxiv.org/pdf/2112.04575), [DAGNN](https://dl.acm.org/doi/pdf/10.1145/3394486.3403076), [GPRGNN](https://arxiv.org/pdf/2006.07988), [ARMAGNN](https://arxiv.org/pdf/1901.01343), [ChebNet](https://papers.nips.cc/paper_files/paper/2016/file/04df4d434d481c5bb723be1b6df1ee65-Paper.pdf), [ChebNetII](https://arxiv.org/pdf/2202.03580), [HornerGCN/ClenshawGCN](https://arxiv.org/pdf/2210.16508), [BernNet](https://arxiv.org/pdf/2106.10994), [LegendreNet](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10160025), [JacobiConv](https://arxiv.org/pdf/2205.11172), [FavardGNN/OptBasisGNN](https://arxiv.org/pdf/2302.12432)|
-|Filter Bank|[AdaGNN](https://arxiv.org/pdf/2104.12840), [FBGNN](https://arxiv.org/pdf/2008.08844), [ACMGNN](https://arxiv.org/pdf/2210.07606), [FAGCN](https://arxiv.org/pdf/2101.00797), [G$^2$CN](https://proceedings.mlr.press/v162/li22h/li22h.pdf), [GNN-LF/HF](https://arxiv.org/pdf/2101.11859), [FiGURe](https://arxiv.org/pdf/2310.01892)|
+| Fixed Filter | [GCN](https://arxiv.org/abs/1609.02907), [SGC](https://arxiv.org/pdf/1902.07153), [gfNN](https://arxiv.org/pdf/1905.09550), [GZoom](https://arxiv.org/pdf/1910.02370), [S²GC](https://openreview.net/pdf?id=CYO5T-YjWZV),[GLP](https://arxiv.org/pdf/1901.09993), [APPNP](https://arxiv.org/pdf/1810.05997), [GCNII](https://arxiv.org/pdf/2007.02133), [GDC](https://proceedings.neurips.cc/paper_files/paper/2019/file/23c894276a2c5a16470e6a31f4618d73-Paper.pdf), [DGC](https://arxiv.org/pdf/2102.10739), [AGP](https://arxiv.org/pdf/2106.03058), [GRAND+](https://arxiv.org/pdf/2203.06389)|
+|Variable Filter|[GIN](https://arxiv.org/pdf/1810.00826), [AKGNN](https://arxiv.org/pdf/2112.04575), [DAGNN](https://dl.acm.org/doi/pdf/10.1145/3394486.3403076), [GPRGNN](https://arxiv.org/pdf/2006.07988), [ARMAGNN](https://arxiv.org/pdf/1901.01343), [ChebNet](https://papers.nips.cc/paper_files/paper/2016/file/04df4d434d481c5bb723be1b6df1ee65-Paper.pdf), [ChebNetII](https://arxiv.org/pdf/2202.03580), [HornerGCN / ClenshawGCN](https://arxiv.org/pdf/2210.16508), [BernNet](https://arxiv.org/pdf/2106.10994), [LegendreNet](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10160025), [JacobiConv](https://arxiv.org/pdf/2205.11172), [FavardGNN / OptBasisGNN](https://arxiv.org/pdf/2302.12432)|
+|Filter Bank|[AdaGNN](https://arxiv.org/pdf/2104.12840), [FBGNN](https://arxiv.org/pdf/2008.08844), [ACMGNN](https://arxiv.org/pdf/2210.07606), [FAGCN](https://arxiv.org/pdf/2101.00797), [G²CN](https://proceedings.mlr.press/v162/li22h/li22h.pdf), [GNN-LF/HF](https://arxiv.org/pdf/2101.11859), [FiGURe](https://arxiv.org/pdf/2310.01892)|
 
 
 ### Covered Datasets
@@ -237,5 +237,5 @@ out = model(x, edge_index)
 
 ## Misc
 - This project is licensed under the [MIT LICENSE](LICENSE).
-- Use "Cite this repository" in the right sidebar for [CITATION](docs/CITATION.cff)
+- Please export [CITATION](docs/CITATION.cff) by using "Cite this repository" in the right sidebar.
 <!-- - Please refer to the [CONTRIBUTING](docs/CONTRIBUTING.md) guide for contributing to this project. -->

docs/source/_include/benchmark.dataset_process.rst

@@ -1,5 +1,5 @@
 benchmark.dataset\_process
-========================
+==================================
 
 .. automodule:: benchmark.dataset_process
    :members:

docs/source/_include/benchmark.trainer.rst

@@ -1,5 +1,5 @@
 benchmark.trainer
-===============
+=========================
 
 .. automodule:: benchmark.trainer
    :members:
@@ -8,16 +8,17 @@ benchmark.trainer
    :private-members:
 
 benchmark.trainer.base
--------------------
+------------------------------
 
 .. automodule:: benchmark.trainer.base
    :members:
    :undoc-members:
    :show-inheritance:
    :private-members:
+   :no-index:
 
 benchmark.trainer.filter
----------------------
+--------------------------------
 
 .. automodule:: benchmark.trainer.filter
    :members:
@@ -26,7 +27,7 @@ benchmark.trainer.filter
    :private-members:
 
 benchmark.trainer.load\_data
--------------------------
+------------------------------------
 
 .. automodule:: benchmark.trainer.load_data
    :members:
@@ -35,7 +36,7 @@ benchmark.trainer.load\_data
    :private-members:
 
 benchmark.trainer.load\_metric
----------------------------
+--------------------------------------
 
 .. automodule:: benchmark.trainer.load_metric
    :members:
@@ -44,7 +45,7 @@ benchmark.trainer.load\_metric
    :private-members:
 
 benchmark.trainer.load\_model
---------------------------
+-------------------------------------
 
 .. automodule:: benchmark.trainer.load_model
    :members:

docs/source/_include/benchmark.utils.rst

@@ -1,5 +1,5 @@
 benchmark.utils
-=============
+=======================
 
 .. automodule:: benchmark.utils
    :members:
@@ -9,7 +9,7 @@ benchmark.utils
 
 
 benchmark.utils.config
--------------------
+------------------------------
 
 .. autosummary::
    :recursive:

docs/source/conf.py

@@ -14,8 +14,9 @@
 author = 'Ningyi Liao'
 release = '1.0.0'
 
-sys.path.insert(0, osp.abspath('../../'))
-sys.path.insert(1, osp.abspath('../../benchmark'))
+proot = osp.abspath(osp.dirname(osp.dirname(osp.dirname((osp.realpath(__file__))))))
+sys.path.insert(0, proot)
+sys.path.insert(1, osp.join(proot, 'benchmark'))
 # sys.path.append(osp.join(osp.dirname(pyg_sphinx_theme.__file__), 'extension'))
 
 # -- General configuration ---------------------------------------------------

docs/source/index.rst

@@ -16,21 +16,21 @@ pyg_spectral
 
    * **High scalability**: As spectral GNNs are inherently suitable for large-scale learning, our framework is feasible to common scalable learning schemes and acceleration techniques. Several spectral-oriented approximation algorithms are also supported.
 
-.. include:: installation.rst
+.. include:: _tutorial/installation.rst
    :end-before: Advanced Options
 
 For advanced options, please refer to `Installation Options <installation.html#advanced-options>`_.
 
-.. include:: reproduce.rst
+.. include:: _tutorial/reproduce.rst
 
 .. toctree::
    :maxdepth: 2
    :caption: Getting Started
 
-   installation
-   reproduce
-   customization
-   arrangement
+   _tutorial/installation
+   _tutorial/reproduce
+   _tutorial/customization
+   _tutorial/arrangement
 
 .. toctree::
    :hidden:

pyg_spectral/utils/loader.py

@@ -1,7 +1,9 @@
+import importlib
+
 
 def load_import(class_name, module_name):
-    r"""Simple hack for dynamic importing module.class"""
-    module = __import__(module_name, fromlist=[class_name])
+    r"""Simple dynamic import for 'module.class'"""
+    module = importlib.import_module(module_name)
     class_obj = getattr(module, class_name)
     if isinstance(class_obj, type):
         return class_obj

pyproject.toml

@@ -21,8 +21,6 @@ classifiers=[
   "License :: OSI Approved :: MIT License",
   "Environment :: GPU :: NVIDIA CUDA :: 12",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.8",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
@@ -32,7 +30,7 @@ keywords=[
     "graph-neural-networks",
     "spectral-gnn",
 ]
-requires-python=">=3.8"
+requires-python=">=3.10"
 dependencies=[
     "torch_geometric>=2.5.3",
     "pandas>=2.0",