通用 |
关系预测 |
RGCN |
《Modeling Relational Data with Graph Convolutional Networks》 |
rgcn_pytorch_implementation |
通用 |
关系预测 |
SEAL |
《Link Prediction Based on Graph Neural Networks》 |
SEAL |
通用 |
节点分类 |
|
|
|
通用 |
社区检测 |
|
《Improved Community Detection using Deep Embeddings from Multilayer Graphs》 |
|
通用 |
社区检测 |
Hierarchical GNN |
《Supervised Community Detection with Hierarchical Graph Neural Networks》 |
|
通用 |
图分类 |
|
《Graph Classification using Structural Attention》 |
|
通用 |
图分类 |
DGCNN |
《An End-to-End Deep Learning Architecture for Graph Classification》 |
pytorch_DGCNN |
通用 |
推荐 |
GCN |
《Graph Convolutional Neural Networks for Web-Scale Recommender Systems》 |
|
通用 |
图生成 |
NetGAN |
《 Net-gan: Generating graphs via random walks》 |
|
通用 |
图生成 |
GraphRNN |
《GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models》 |
|
通用 |
图生成 |
MolGAN |
《 Molgan: An implicit generative model for small molecular graphs》 |
|
决策优化 |
旅行商问题 |
GNN |
《Learning to Solve NP-Complete Problems: A Graph Neural Network for Decision TSP》《Attention solves your tsp》 |
https://github.com/machine-reasoning-ufrgs/TSP-GNN https://github.com/wouterkool/attention-tsp |
决策优化 |
规划器调度 |
GNN |
《Adaptive Planner Scheduling with Graph Neural Networks》《Revised note on learning quadratic assignment with graph neural networks》 |
|
决策优化 |
组合优化 |
GCN structure2vec |
《Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search》《 Learning combinatorial optimization algorithms over graphs》 |
NPHard |
交通 |
出租车需求预测 |
|
《Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction》 |
DMVST-Net |
交通 |
交通流量预测 |
|
《Spatio-Temporal Graph Convolutional Networks:A Deep Learning Framework for Traffic Forecasting》 |
STGCN-PyTorch |
交通 |
交通流量预测 |
|
《DIFFUSION CONVOLUTIONAL RECURRENT NEURAL NETWORK: DATA-DRIVEN TRAFFIC FORECASTING》 |
DCRNN |
传感网络 |
传感器布局 |
|
《Distributed Graph Layout for Sensor Networks》 |
|
区域安全 |
疾病传播 |
|
《Predicting and controlling infectious disease epidemics using temporal networks》 |
|
区域安全 |
城市人流预测 |
|
《FCCF: Forecasting Citywide Crowd Flows Based on Big Data》 |
|
社交网络 |
影响力预测 |
GCN/GAT |
《DeepInf: Social Influence Prediction with Deep Learning》 |
DeepInf |
社交网络 |
转发动作预测 |
|
《Social Influence Locality for Modeling Retweeting Behaviors》 |
|
社交网络 |
转发动作预测 |
|
《 Predicting Retweet via Social Influence Locality》 |
|
文本 |
文本分类 |
GCN |
"《Diffusion-convolutional neural networks》《 Convolutionalneural networks on graphs with fast localized spectral filtering》《Knowledgetransfer for out-of-knowledge-base entities : A graph neuralnetwork approach》《 Deep convolutional networks on graph-structured data》《 Semi-supervised classification with graph convolutional networks》《 Geometric deep learning on graphs and manifolds using mixture model cnns》" |
dcnn-tensorflow |
文本 |
文本分类 |
GAT |
《Graph attention networks》 |
|
文本 |
文本分类 |
DGCNN |
《Large-scale hierarchical text classification with recursively regularized deep graph-cnn》 |
DeepGraphCNNforTexts |
文本 |
文本分类 |
Text GCN |
《Graph convolutional networks for text classification》 |
text_gcn |
文本 |
文本分类 |
Sentence LSTM |
《 Sentence-state LSTM for text representation》 |
S-LSTM |
文本 |
序列标注(POS, NER) Sentence LSTM |
《 Sentence-state LSTM for textrepresentation》 |
https://github.com/leuchine/S-LSTM |
|
文本 |
语义分类 |
LSTM |
《 Improved semantic representations from tree-structured long short-term memorynetworks》 |
https://github.com/ttpro1995/TreeLSTMSentiment |
文本 |
语义角色标注Syntactic |
GCN |
《Encoding sentences with graph convolutional networks for semantic role labeling》 |
|
文本 |
机器翻译 |
GCN |
《Graph convolutional encoders for syntax-aware neural machine translation》/《 Exploiting semantics in neural machine translation with graph convolutional networks》" |
|
文本 |
机器翻译 |
GGNN |
《 Graph-to-sequence learningusing gated graph neural networks. 》 |
https://github.com/beckdaniel/acl2018_graph2seq |
文本 |
关系抽取 |
LSTM |
《 End-to-end relation extraction usinglstms on sequences and tree structures》 |
|
文本 |
关系抽取 |
Graph LSTM |
《Crosssentencen-ary relation extraction with graph lstms》/《 N-ary relationextraction using graph state lstm》 |
https://github.com/freesunshine0316/nary-grn |
文本 |
关系抽取 |
GCN |
《 Graph convolution over pruned dependency trees improves relation extraction》 |
https://github.com/qipeng/gcn-over-pruned-trees |
文本 |
事件抽取 |
GCN |
《 Jointly multiple events extractionvia attention-based graph information aggregation》/《. Graph convolutional networks with argument-aware pooling for event detection》 |
https://github.com/lx865712528/JMEE |
文本 |
文本生成 |
Sentence LSTM |
《A graph-to-sequence mdel for amr-to-text generation》 |
|
文本 |
文本生成 |
GGNN |
《 Graph-to-sequence learningusing gated graph neural networks》 |
|
文本 |
阅读理解 |
Sentence LSTM |
《Exploring graph-structured passage representation for multihop reading comprehension with graph neural networks》 |
|
图像/视频 |
社会关系理解 |
GRM |
《Deep reasoning with knowledge graph for social relationship understanding》 |
https://github.com/wzhouxiff/SR |
图像/视频 |
图像分类 |
GCN |
《 Few-shot learning with graph neuralnetworks》/《Zero-shot recognition via semantic embeddings and knowledge graphs》 |
https://github.com/louis2889184/gnn_few_shot_cifar100 https://github.com/JudyYe/zero-shot-gcn |
图像/视频 |
图像分类 |
GGNN |
《 Multi-label zero-shot learning with structured knowledge graphs》 |
https://people.csail.mit.edu/weifang/project/vll18-mlzsl/ |
图像/视频 |
图像分类 |
ADGPM |
《Rethinking knowledge graph propagation for zero-shot learning》 |
https://github.com/cyvius96/adgpm |
图像/视频 |
图像分类 |
GSNN |
《The more you know: Using knowledge graphs for image classification》 |
https://github.com/KMarino/GSNN_TMYN |
图像/视频 |
视觉问答 |
GGNN |
《Graph-structured representations for visual question answering》/《Deep reasoning with knowledge graph for social relationship understanding》 " |
|
图像/视频 |
领域识别 |
GCNN |
《Iterative visual reasoning beyond convolutions》 |
https://github.com/coderSkyChen/Iterative-Visual-Reasoning.pytorch |
图像/视频 |
语义分割 |
Graph LSTM |
《 Interpretablestructure-evolving lstm》《 Semantic objectparsing with graph lstm》 |
|
图像/视频 |
语义分割 |
GGNN |
《Large-scale point cloud semantic segmentation with superpoint graphs》 |
https://github.com/loicland/superpoint_graph |
图像/视频 |
语义分割 |
DGCNN |
《Dynamic graph cnn for learning on point clouds》 |
https://github.com/af13s/dgcnn-amino |
图像/视频 |
语义分割 |
3DGNN |
《 3d graph neural networks for rgbd semantic segmentation》 |
https://github.com/yanx27/3DGNN_pytorch |
生物科技 |
物理系统 |
IN |
《 Interaction networks for learning about objects, relations and physics》 |
https://github.com/higgsfield/interaction_network_pytorch https://github.com/jaesik817/Interaction-networks_tensorflow |
生物科技 |
物理系统 |
VIN |
《 Visual interaction networks: Learning a physics simulator from video》 |
|
生物科技 |
物理系统 |
GN |
《 Graph networks as learnable physics engines for inference and control》 |
https://github.com/fxia22/gn.pytorch |
生物科技 |
分子指纹 |
GCN |
《Convolutional networks on graphs for learning molecular fingerprints》 |
https://github.com/fllinares/neural_fingerprints_tf |
生物科技 |
分子指纹 |
NGF |
《Molecular graph convolutions: moving beyond fingerprints》 |
|
生物科技 |
蛋白质界面预测 |
GCN |
《Protein interfaceprediction using graph convolutional networks》 |
https://github.com/fouticus/pipgcn |
生物科技 |
药物副作用预测 |
Decagon |
《Modeling polypharmacyside effects with graph convolutional networks》 |
https://github.com/miliana/DecagonPython3 |
生物科技 |
疾病分类 |
PPIN |
《Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification》 |
|