3DInfomaxMaking self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.
Stars: ✭ 107 (-35.15%)
Mutual labels: molecules, graph-neural-networks, graph-representation-learning, gnn
StellargraphStellarGraph - Machine Learning on Graphs
Stars: ✭ 2,235 (+1254.55%)
Mutual labels: graphs, geometric-deep-learning, graph-neural-networks
awesome-efficient-gnnCode and resources on scalable and efficient Graph Neural Networks
Stars: ✭ 498 (+201.82%)
Mutual labels: graph-neural-networks, graph-representation-learning, gnn
PDNThe official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Stars: ✭ 44 (-73.33%)
Mutual labels: molecules, message-passing, gnn
GNN-Recommender-SystemsAn index of recommendation algorithms that are based on Graph Neural Networks.
Stars: ✭ 505 (+206.06%)
Mutual labels: graph-neural-networks, graph-representation-learning, gnn
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).
Stars: ✭ 85 (-48.48%)
Mutual labels: attention, graph-neural-networks, gnn
how attentive are gatsCode for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)
Stars: ✭ 200 (+21.21%)
Mutual labels: attention, graph-neural-networks
GNNLens2Visualization tool for Graph Neural Networks
Stars: ✭ 155 (-6.06%)
Mutual labels: graph-neural-networks, graph-representation-learning
ntds 2019Material for the EPFL master course "A Network Tour of Data Science", edition 2019.
Stars: ✭ 62 (-62.42%)
Mutual labels: graphs, graph-neural-networks
EvalneSource code for EvalNE, a Python library for evaluating Network Embedding methods.
Stars: ✭ 67 (-59.39%)
Mutual labels: graphs, representation-learning
CausingCausing: CAUsal INterpretation using Graphs
Stars: ✭ 47 (-71.52%)
Mutual labels: graphs, gnn
BGCNA Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).
Stars: ✭ 129 (-21.82%)
Mutual labels: graph-neural-networks, gnn
COCO-LM[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Stars: ✭ 109 (-33.94%)
Mutual labels: transformers, representation-learning
graphml-tutorialsTutorials for Machine Learning on Graphs
Stars: ✭ 125 (-24.24%)
Mutual labels: representation-learning, graph-neural-networks
LPGNNLocally Private Graph Neural Networks (ACM CCS 2021)
Stars: ✭ 30 (-81.82%)
Mutual labels: graph-neural-networks, graph-deep-learning
SubGNNSubgraph Neural Networks (NeurIPS 2020)
Stars: ✭ 136 (-17.58%)
Mutual labels: graph-neural-networks, graph-representation-learning
QGNNQuaternion Graph Neural Networks (ACML 2021) (Pytorch and Tensorflow)
Stars: ✭ 31 (-81.21%)
Mutual labels: graph-neural-networks, graph-representation-learning
iPerceiveApplying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering | Python3 | PyTorch | CNNs | Causality | Reasoning | LSTMs | Transformers | Multi-Head Self Attention | Published in IEEE Winter Conference on Applications of Computer Vision (WACV) 2021
Stars: ✭ 52 (-68.48%)
Mutual labels: transformers, attention
gcnn kerasGraph convolution with tf.keras
Stars: ✭ 47 (-71.52%)
Mutual labels: graphs, molecules