Awesome graph classification
A curated collection of graph classification papers with implementations covering embeddings, deep learning, kernels, and factorization.
What is Awesome graph classification?
Awesome Graph Classification is a curated collection of research papers and reference implementations focused on graph classification methods. It covers approaches including graph embeddings, deep learning models, graph kernels, and matrix factorization techniques for analyzing graph-structured data. The repository serves as a comprehensive resource for understanding and applying state-of-the-art graph classification algorithms.
Machine learning researchers, data scientists, and practitioners working with graph-structured data who need to implement or benchmark graph classification methods. It's particularly valuable for those entering the field of graph machine learning or looking for reproducible implementations of academic papers.
This collection provides carefully curated papers with working implementations, saving researchers time searching for reliable code. Unlike generic paper lists, it focuses specifically on graph classification with practical implementations, making it easier to reproduce results and build upon existing research.
Overview
A collection of important graph embedding, classification and representation learning papers with implementations.
Use Cases
Best For
- Finding reference implementations of graph classification papers
- Comparing different graph embedding techniques for classification tasks
- Reproducing results from graph deep learning research
- Benchmarking graph kernel methods on standard datasets
- Learning about matrix factorization approaches for graph representation
- Exploring spectral methods for graph fingerprinting and classification
Not Ideal For
- Production teams needing a single, unified library with active maintenance and documentation
- Beginners seeking interactive tutorials or guided learning paths for graph machine learning
- Researchers requiring the absolute latest papers published in real-time
Pros & Cons
Pros
Covers matrix factorization, spectral fingerprints, deep learning, and graph kernels across four dedicated chapters, offering a broad overview of graph classification approaches.
Each listed paper includes reference code, enabling reproducibility and hands-on experimentation, as highlighted in the repository's focus on working implementations.
Provides links to benchmark graph classification datasets, facilitating consistent evaluation and comparison of methods, as mentioned in the README's dataset section.
Follows the awesome list philosophy to include only high-quality papers with code, saving time for researchers by filtering out less reliable resources.
Cons
Implementations are from disparate sources, leading to inconsistent coding styles, varying dependencies, and complex setup processes for each method.
As a curated list, it may not be updated frequently enough to include the most recent advancements in fast-evolving areas like graph deep learning.
No integrated framework or documentation exists; users must adapt each implementation separately, increasing the effort for practical deployment.
Frequently Asked Questions
Related Projects
vintaAn opinionated list of Python frameworks, libraries, tools, and resources
awesome-public-datasetsA topic-centric list of HQ open datasets.
awesome-machine-learningA curated list of awesome Machine Learning frameworks, libraries and software.
awesome-awesomenessA curated list of awesome awesomeness
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.