Deep learning for dynamic graphs: models and benchmarks

Official code repository for our paper "Deep learning for dynamic graphs: models and benchmarks" accepted at the IEEE Transactions on Neural Networks and Learning Systems.

Please consider citing us

@article{gravina2024benchmark,
    author={Gravina, Alessio and Bacciu, Davide},
    journal={IEEE Transactions on Neural Networks and Learning Systems}, 
    title={{Deep Learning for Dynamic Graphs: Models and Benchmarks}}, 
    year={2024},
    volume={},
    number={},
    pages={1-14},
    keywords={Surveys;Representation learning;Benchmark testing;Laplace equations;Graph neural networks;Message passing;Convolution;Benchmark;deep graph networks (DGNs);dynamic graphs;graph neural networks (GNNs);survey;temporal graphs},
    doi={10.1109/TNNLS.2024.3379735}
}

How to run the experiments

To reproduce the experiments please refer to:

• D-TDG/README.md to reproduce the experiments on the Discrete-Time Dynamic Graph domain.
• C-TDG/README.md to reproduce the experiments on the Continuous-Time Dynamic Graph domain.