This repository serves as a curated, continuously updated collection of essential research papers and tracking on the progress of Graph Neural Networks (GNNs). It aims to assist researchers and practitioners in navigating the rapidly evolving field of GNNs, which are crucial for analyzing graph-structured data across diverse domains like social networks, bioinformatics, and computer vision.

How It Works

The project compiles a comprehensive list of seminal and recent papers, categorizing them by publication venue (journals, conferences, arXiv). It highlights key GNN concepts and their applications, providing a structured overview of the field's advancements. The repository emphasizes the growing importance and widespread adoption of GNNs, citing the significant impact of foundational works like Kipf and Welling's GCN.

Quick Start & Requirements

This repository is a curated list of papers and does not involve direct code execution or installation. All listed papers are publicly available.

Highlighted Details

• Extensive lists of journal, conference, and arXiv papers covering GNN methods and applications from 2015 to 2023.
• Includes links to code for many foundational papers.
• Features a directory of popular open-source GNN platforms like DGL, PyTorch Geometric, and Graph Nets.
• Tracks the citation count of key GNN papers, demonstrating their impact.

Maintenance & Community

The project is contributed to by Allen Bluce and Anne Bluce, with contact information provided for feedback and issues. The latest update was on March 28, 2023.

Licensing & Compatibility

The repository itself does not specify a license. The linked papers are subject to their respective publication licenses.

Limitations & Caveats

The repository is a curated list and does not provide implementations or benchmarks. The "progress" is based on the inclusion of papers, and the completeness of the list is subjective.