#jupyter_notebook #benchmark_framework #deep_learning #dgl #graph_deep_learning #graph_neural_networks #graph_representation_learning #pytorch

https://github.com/graphdeeplearning/benchmarking-gnns

#python #deep_learning #feature_matching #graph_neural_networks #pose_estimation

https://github.com/magicleap/SuperGluePretrainedNetwork

#python #automl #graph_neural_networks #hyper_parameter_optimization #pytorch #pytorch_geometric

https://github.com/THUMNLab/AutoGL

#other #graph_convolutional_networks #graph_neural_networks #graph_representation_learning #scalable_deep_learning #gnn #efficient_neural_networks #efficient_deep_learning

https://github.com/chaitjo/awesome-efficient-gnn

#python #deep_learning #pytorch #drug_discovery #graph_neural_networks

https://github.com/DeepGraphLearning/torchdrug

#rust #analytics #big_data #data_science #graph #graph_analytics #graph_computation #graph_computing #graph_data #graph_neural_networks #gremlin

https://github.com/alibaba/GraphScope

#python #deep_learning #graph_neural_networks

DGL (Deep Graph Library) is a powerful and easy-to-use Python package for deep learning on graphs. It allows you to work with graphs on both CPU and GPU, making it highly scalable and efficient, even for large-scale graphs. DGL is compatible with major frameworks like PyTorch, Apache MXNet, and TensorFlow, giving you flexibility in your projects.

The benefits include DGL optimizes communication, memory consumption, and synchronization, allowing it to handle billion-sized graphs efficiently.
- **Ease of Use** DGL offers a variety of functions for computing with graph objects and includes state-of-the-art GNN models and modules.
- **Community Support**: Active community channels like Slack, forums, and monthly seminars help you stay connected and get support when needed.

Overall, DGL simplifies the process of working with graph neural networks, making it a valuable tool for researchers and practitioners alike.

https://github.com/dmlc/dgl

#python #deep_learning #geometric_deep_learning #graph_convolutional_networks #graph_neural_networks #pytorch

PyG (PyTorch Geometric) is a library that makes it easy to work with Graph Neural Networks (GNNs) using PyTorch. Here’s why it’s beneficial You can start training a GNN model with just 10-20 lines of code, especially if you're already familiar with PyTorch.
- **Comprehensive Models** The library supports large-scale graphs, dynamic graphs, and heterogeneous graphs, making it versatile for various applications.
- **Scalability** It provides extensive documentation, tutorials, and examples to help you get started quickly.

Overall, PyG simplifies the process of working with GNNs, making it a powerful tool for machine learning on graph-structured data.

https://github.com/pyg-team/pytorch_geometric