pytorch-geometric 开源项目推荐（682 个）

c2g-dev /city2graph

将地理空间关系转换为图，用于图神经网络和空间网络分析

a-r-j /graphein

蛋白质图库

THUMNLab /AutoGL

用于图形机器学习的autoML框架和工具包。

chaitjo /geometric-gnn-dojo

Geometric GNN Dojo 提供统一实现与实验，用于探索几何图神经网络的设计空间（ICML 2023）

mlabonne /graph-neural-network-course

使用 PyTorch Geometric 的图神经网络免费实践课程。

lukecavabarrett /pna

在 PyTorch、DGL 和 PyTorch Geometric 中实现用于图神经网络的 Principal Neighbourhood Aggregation

yuyangw /MolCLR

在 PyG 中实现 MolCLR：“基于图神经网络的分子表示对比学习”。

chaitjo /geometric-rna-design

gRNAde 是一个用于 3D RNA 结构与功能逆向设计的生成式 AI 框架

qitianwu /DIFFormer

The official implementation for ICLR2023 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"

qitianwu /NodeFormer

The official implementation of NeurIPS2022 spotlight paper "NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification"

bknyaz /graph_attention_pool

Attention over nodes in Graph Neural Networks using PyTorch [NeurIPS 2019]

benedekrozemberczki /SGCN

A PyTorch implementation of "Signed Graph Convolutional Network" (ICDM 2018).

drprojects /DeepViewAgg

[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in "Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation"

divelab /GOOD

GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]

XiaShan1227 /GNN-Tutorial

B站GNN教程资料

HannesStark /3DInfomax

利用分子的三维几何结构预训练GNNs，使自监督学习能够实现。已在DGL和Pytorch几何中实现。

rusty1s /pyg_autoscale

Implementation of "GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings" in PyTorch

SherylHYX /pytorch_geometric_signed_directed

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.

BorgwardtLab /TOGL

Topological Graph Neural Networks (ICLR 2022)

mukhlishga /gnn-powerflow

图神经网络在交流潮流计算预测中的应用。使用 Pytorch Geometric 框架开发。我的埃因霍温理工大学硕士论文。