GnnpapersMust-read papers on graph neural networks (GNN)
gnnTensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
mtad-gat-pytorchPyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).
Meta-Fine-Tuning[CVPR 2020 VL3] The repository for meta fine-tuning in cross-domain few-shot learning.
gemnet pytorchGemNet model in PyTorch, as proposed in "GemNet: Universal Directional Graph Neural Networks for Molecules" (NeurIPS 2021)
VectorNetPytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”
PDNThe official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
staginSTAGIN: Spatio-Temporal Attention Graph Isomorphism Network
gnn-lspeSource code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
GCLList of Publications in Graph Contrastive Learning
gnn-re-rankingA real-time GNN-based method. Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
BasicGNNTrackingThis shows a basic implementation of the global nearest neighbour (GNN) multi target Tracker. Kalman filter is used for Tracking and Auction Algorithm for determining the assignment of measurments to filters.
BGCNA Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).
dgcnnClean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).
mmgnn textvqaA Pytorch implementation of CVPR 2020 paper: Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
ncemLearning cell communication from spatial graphs of cells
CausingCausing: CAUsal INterpretation using Graphs
spatio-temporal-brainA Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in rs-fMRI Data
3DInfomaxMaking self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.
GraphMixCode for reproducing results in GraphMix paper