graphdeeplearning/benchmarking-gnns
Benchmarking framework for evaluating graph neural network architectures across multiple datasets.
Not currently ranked — collecting fresh signals.
star history
This repository provides a standardized benchmarking framework for Graph Neural Networks (GNNs), enabling reproducible evaluation of different GNN architectures on tasks including molecular property prediction (ZINC, AQSOL), graph classification (PATTERN, CLUSTER), and mathematical graph theory problems. The framework uses DGL (Deep Graph Library) and PyTorch as backend, supports both CPU and GPU environments, and includes datasets and leaderboards for comparing model performance.
Frequently asked
- What is graphdeeplearning/benchmarking-gnns?
- Benchmarking framework for evaluating graph neural network architectures across multiple datasets.
- Is benchmarking-gnns open source?
- Yes — graphdeeplearning/benchmarking-gnns is open source, released under the MIT license.
- What language is benchmarking-gnns written in?
- graphdeeplearning/benchmarking-gnns is primarily written in Jupyter Notebook.
- How popular is benchmarking-gnns?
- graphdeeplearning/benchmarking-gnns has 2.7k stars on GitHub.
- Where can I find benchmarking-gnns?
- graphdeeplearning/benchmarking-gnns is on GitHub at https://github.com/graphdeeplearning/benchmarking-gnns.