---

Overview • Installation • Examples • Docs • Citation

OpenGSL

Official code for OpenGSL: A Comprehensive Benchmark for Graph Structure Learning. OpenGSL is a comprehensive benchmark for Graph Structure Learning(GSL). GSL is a family of data-centric learning approaches which jointly optimize the graph structure and the corresponding GNN models. It has great potential in many real-world applications, including disease analysis, protein structure prediction, etc.

Overview of the Benchmark

OpenGSL provides a fair and comprehensive platform to evaluate existing GSL works and facilitate future GSL research.

Installation

Note: OpenGSL depends on PyTorch, PyTorch Geometric, PyTorch Sparse and DEEP GRAPH LIBRARY (DGL). To streamline the installation, OpenGSL does NOT install these libraries for you. Please install them from the above links for running OpenGSL:

• torch>=1.9.1
• torch_geometric>=2.1.0
• torch_sparse>=0.6.12
• dgl>=0.9.0

Installing with Pip

pip install opengsl

Installation for local development:

git clone https://github.com/OpenGSL/OpenGSL
cd opengsl
pip install -e .

Required Dependencies:

• Python 3.7+
• ruamel.yaml
• pandas
• scipy
• scikit-learn
• pyro-api
• pyro-ppl
• numba

🚀Quick Start

You can use the command python examples/gcn_cora.py or follow the 4 steps.

The following example shows you how to run GRCN on the Cora dataset.

Step 1: Load configuration

import opengsl
conf = opengsl.config.load_conf(method="grcn", dataset="cora")

Method and Dataset parameters in Built-in configuration (Updated Frequently)

method ： gcn, prognn, idgl, grcn, gaug, slaps, nodeformer, gen, cogsl, segsl, sublime, stable, wsgnn, glcn, bmgcn

dataset ： cora, pubmed, citeseer, blogcatalog, flickr, amazon-ratings, questions, minesweeper, roman-empire, wiki-cooc, wikics

Step 2: Load data

dataset = opengsl.data.Dataset("cora", n_splits=1, feat_norm=conf.dataset['feat_norm'])

Step 3: Build Model

solver = opengsl.method.GRCNSolver(conf,dataset)

Step 4: Training and Evaluation

exp = opengsl.ExpManager(solver)
exp.run(n_runs = 10)

⚙️Build Your Own GSL

OpenGSL provides an easy way to build GSL algorithm based on several components.

if you want to learn how to build own GSL method, see Build Your Own GSL.ipynb for more details.

📱️Updates

2023.12.21 Update new method PASTEL(CIKM22).

2023.11.27 Update new method PROSE(KDD23).

2023.11.1 Version 0.0.6 available!

• A General GSL model added.
• New GSL methods WSGNN, GLCN and BMGCN added.
• New datasets including Wikics, Ogbn-arxiv and CSBM synthetic graphs.
• APPNP and GIN can be used as backbones for various GSL methods.
• Other minor updates.

How to Contribute

As an active research topic, we are witnessing the rapid development of GSL methods. Hence, this project will be frequently updated, and we welcome everyone interested in this topic to contribute!

Please feel free to send PR or issue!

Citation

Our paper on this benchmark will be released soon!

If you use our benchmark in your works, we would appreciate citations to the paper:

@article{zhou2023opengsl,
  title={OpenGSL: A Comprehensive Benchmark for Graph Structure Learning},
  author={Zhiyao Zhou, Sheng Zhou, Bochao Mao, Xuanyi Zhou, Jiawei Chen, Qiaoyu Tan, Daochen Zha, Can Wang, Yan Feng, Chun Chen},
  journal={arXiv preprint arXiv:2306.10280},
  year={2023}
}

Reference

ID	Paper	Method	Conference
1	Semi-supervised classification with graph convolutional networks	GCN	ICLR 2017
2	Learning Discrete Structures for Graph Neural Networks	LDS	ICML 2019
3	Graph Structure Learning for Robust Graph Neural Networks	ProGNN	KDD 2020
4	Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings	IDGL	NeurIPS 2020
5	Graph-Revised Convolutional Network	GRCN	ECML-PKDD 2020
6	Data Augmentation for Graph Neural Networks	GAug(O)	AAAI 2021
7	SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks	SLAPS	ICML 2021
8	Variational Inference for Training Graph Neural Networks in Low-Data Regime through Joint Structure-Label Estimation	WSGNN	KDD 2022
9	Nodeformer: A scalable graph structure learning transformer for node classification	Nodeformer	NeurIPS 2022
10	Graph Structure Estimation Neural Networks	GEN	WWW 2021
11	Compact Graph Structure Learning via Mutual Information Compression	CoGSL	WWW 2022
12	SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization	SEGSL	WWW 2023
13	Towards Unsupervised Deep Graph Structure Learning	SUBLIME	WWW 2022
14	Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN	STABLE	KDD 2022
15	Semi-Supervised Learning With Graph Learning-Convolutional Networks	GLCN	CVPR 2019
15	Block Modeling-Guided Graph Convolutional Neural Networks	BM-GCN	AAAI 2022