This repository is a curated list of academic papers focusing on self-supervised learning (SSL) and pretraining techniques for Graph Neural Networks (GNNs). It serves researchers and practitioners in graph representation learning, providing a structured overview of advancements and key contributions in the field, categorized by publication year.

How It Works

The repository compiles research papers that explore various SSL strategies for GNNs, including contrastive learning, generative methods, and predictive tasks. These approaches aim to learn robust graph representations from unlabeled data, enhancing downstream task performance and generalization capabilities. The list highlights extensively cited papers with a fire emoji.

Quick Start & Requirements

This repository is a collection of research papers and does not have a direct installation or execution command. Links to papers and their associated code (where available) are provided for each entry.

Highlighted Details

• Comprehensive categorization of papers by publication year, facilitating historical trend analysis.
• Identification of highly influential papers (over 80 citations) to guide focus.
• Inclusion of direct links to research papers and, where available, their corresponding code repositories.
• Covers a wide range of applications, from molecular property prediction to recommendation systems and anomaly detection.

Maintenance & Community

The repository is maintained by Wei Jin, Yuning You, and Yingheng Wang. Contributions and corrections are welcomed via issues or pull requests.

Licensing & Compatibility

The repository itself is not software and does not have a license. Individual papers and their associated code would be governed by their respective licenses.

Limitations & Caveats

This is a curated list of papers and does not provide any executable code or framework. The "hotness" metric (fire emoji) is based on citation count, which may not always reflect current relevance or impact.