torch-geometric

PyTorch Geometric is a library built on PyTorch for developing and training Graph Neural Networks (GNNs). Apply this skill for deep learning on graphs and irregular structures, including mini-batch processing, multi-GPU training, and geometric deep learning applications.

PyG represents graphs using the torchgeometric.data.Data class with these key attributes:

Important: These attributes are not mandatory—extend Data objects with custom attributes as needed.

圖神經網路（PyG）。節點/圖分類、連結預測、GCN、GAT、GraphSAGE、異構圖、分子屬性預測、用於幾何深度學習。 來源：ovachiever/droid-tings。