Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/n-kats/awesome-gtnn

Lists of awesome resources for geometric or topological neural network
https://github.com/n-kats/awesome-gtnn

List: awesome-gtnn

Last synced: 16 days ago
JSON representation

Lists of awesome resources for geometric or topological neural network

Awesome Lists containing this project

README 

        
# awesome-GTNN

Lists of awesome resources for geometric or topological neural network



## theme

* graph

* point cloud

* social net

* mesh

* chemistry

* depth

* TDA

* autoML



## neural network

* https://github.com/deepmind/graph_nets

* https://github.com/rusty1s/pytorch_geometric

* https://github.com/facebookresearch/PyTorch-BigGraph

* https://github.com/pfnet-research/chainer-chemistry

* https://github.com/dmlc/dgl

* https://github.com/tensorflow/graphics



### others

* https://github.com/matenure/FastGCN

* https://github.com/ethanfetaya/NRI

* https://github.com/Eilene/GWNN

* https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork

* https://github.com/tkipf/gcn

* https://github.com/charlesq34/pointnet

* https://github.com/charlesq34/pointnet2

* https://github.com/yewzijian/3DFeatNet

* https://github.com/shaohua0116/Multiview2Novelview

* https://github.com/rajammanabrolu/KG-DQN



## automatic model

* https://github.com/melodyguan/enas

* https://github.com/renqianluo/NAO

* https://github.com/quark0/darts



## depth

* https://github.com/tinghuiz/SfMLearner



## TDA

* https://github.com/Ripser/ripser



## knowledge

* https://github.com/EagleW/PaperRobot



## papers

### survey

* [Deep Learning on Graphs: A Survey](https://arxiv.org/abs/1812.04202)

* [Graph Neural Networks: A Review of Methods and Applications](https://arxiv.org/abs/1812.08434)

* [A Comprehensive Survey on Graph Neural Networks](https://arxiv.org/abs/1901.00596)



### graph layer

* [GCN](https://arxiv.org/abs/1609.02907)

* [TreeLSTM](https://arxiv.org/abs/1503.00075)

* [R-GCN](https://arxiv.org/abs/1703.06103)

* [JTNN](https://arxiv.org/abs/1802.04364)

* [LGNN](https://arxiv.org/abs/1705.08415)

* [DGMG](https://arxiv.org/abs/1803.03324)

* [Spline](https://arxiv.org/abs/1711.08920)

* [ChebConv](https://arxiv.org/abs/1606.09375)

* [NNConv](https://arxiv.org/abs/1704.01212)

* [GAT](https://arxiv.org/abs/1710.10903)

* [AGNN](https://arxiv.org/abs/1803.03735)

* [SAGE](https://arxiv.org/abs/1706.02216)

* [GIN](https://arxiv.org/abs/1810.00826)

* [ARMA](https://arxiv.org/abs/1901.01343)

* [RGCN](https://arxiv.org/abs/1703.06103)

* [Edge](https://arxiv.org/abs/1801.07829)

* [GWNN](https://openreview.net/forum?id=H1ewdiR5tQ)

* [GraphWarpModule](https://arxiv.org/abs/1902.01020)

* [GlobalAttention](https://arxiv.org/abs/1511.05493)

* [Set2Set](https://arxiv.org/abs/1511.06391)

* [SortPool](https://www.cse.wustl.edu/~muhan/papers/AAAI_2018_DGCNN.pdf)

* [DenseDifferentiablePooling](https://arxiv.org/abs/1806.08804)

* [GraclusPooing](http://www.cs.utexas.edu/users/inderjit/public_papers/multilevel_pami.pdf)

* [VoxelGridPooing](https://arxiv.org/abs/1704.02901)

* [GMM](https://arxiv.org/abs/1611.08402)

* [Graph U-Net](https://openreview.net/forum?id=HJePRoAct7)

* [TopKPooing](https://arxiv.org/abs/1811.01287)

* [DeepGraphInfomax](https://arxiv.org/abs/1809.10341)

* [graph_nets](https://arxiv.org/abs/1806.01261)

* [simplfying GCN](https://arxiv.org/abs/1902.07153)



### depth

* [SfMLearner](https://arxiv.org/abs/1704.07813)

* [vid2depth](https://arxiv.org/abs/1802.05522)

* [struct2depth](https://arxiv.org/abs/1811.06152)

* [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://arxiv.org/abs/1904.04998)



### generative model

* [MolGAN](https://arxiv.org/abs/1805.11973)

* [GraphVAE](https://arxiv.org/abs/1802.03480)

* [GenerativeGCN for growing graphs](https://arxiv.org/abs/1903.02640)



### 3D-aware neural network

* [HoloGAN](https://arxiv.org/abs/1904.01326)



### point cloud

* [PointNet](https://arxiv.org/abs/1612.00593)

* [PointNet++](https://arxiv.org/abs/1706.02413)

* [PointCNN](https://arxiv.org/abs/1801.07791)

* [Submanifold Sparse Convolutional Networks](https://arxiv.org/abs/1706.01307)

* [3D Graph Embedding Learning with a Structure-aware Loss Function

for Point Cloud Semantic Instance Segmentation](https://arxiv.org/abs/1902.05247)

* [Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds](https://arxiv.org/abs/1802.01500)

* [PCPNET](https://arxiv.org/abs/1710.04954)

* [VoxelNet](https://arxiv.org/abs/1711.06396)

* [Frustum PointNets for 3D Object Detection from RGB-D Data](https://arxiv.org/abs/1711.08488)



### mesh

* [Neural 3D Mesh Renderer](https://arxiv.org/abs/1711.07566)

* [Pixel2Mesh](https://arxiv.org/abs/1804.01654)



### network architecture search

* [NAS](https://arxiv.org/abs/1707.07012)

* [PNAS](https://arxiv.org/abs/1712.00559)

* [ENAS](https://arxiv.org/abs/1802.03268)

* [EPNAS](https://arxiv.org/abs/1808.00391)

* [NAONet](https://arxiv.org/abs/1808.07233)

* [DARTS](https://arxiv.org/abs/1806.09055)

* [GHN](https://arxiv.org/abs/1810.05749)

* [A Differentiable Gaussian-like Distribution on Hyperbolic Space for Gradient-Based Learning](https://arxiv.org/abs/1902.02992)

* [Exploring Randomly Wired Neural Networks for Image Recognitio](https://arxiv.org/abs/1904.01569)



### TDA

* [Beyond topological persistence: Starting from networks](https://arxiv.org/abs/1901.08051v1)

* [Topological Persistence in Geometry and Analysis](https://arxiv.org/abs/1904.04044)

* [PersLay](https://arxiv.org/abs/1904.09378)



### path

* [Extrapolating paths with graph neural networks](https://arxiv.org/abs/1903.07518)



### Applications

* [Context-Aware Visual Compatibility Prediction](https://arxiv.org/abs/1902.03646)

* [NetworkSemanticSegmentation w/ GitHub](https://arxiv.org/abs/1902.05220v1)



### knowledge

* [PaperRobot](https://arxiv.org/abs/1905.07870)



### related

* [Graph Spectral Regularization for Neural Network Interpretability](https://arxiv.org/abs/1810.00424)

* [On the Transferability of Spectral Graph Filters](https://arxiv.org/abs/1901.10524)

* [KG-DGN](https://arxiv.org/abs/1812.01628)

* [Hyperbolic Disk Embeddings for Directed Acyclic Graphs](https://arxiv.org/abs/1902.04335)

* [Graph cohomologies and rational homotopy type of configuration spaces](https://arxiv.org/abs/1904.01452)

* [Topology and curvature of metric spaces](https://arxiv.org/abs/1904.00222)



## dataset

* QM9  

  [MoleculeNet: A Benchmark for Molecular Machine Learning](https://arxiv.org/abs/1703.00564)

  [Neural Message Passing for Quantum Chemistry](https://arxiv.org/abs/1704.01212)

* [ModelNet](http://modelnet.cs.princeton.edu/)[[format](http://segeval.cs.princeton.edu/public/off_format.html)]

* [semanticscholar](http://labs.semanticscholar.org/corpus/)

* [semanticscholar api](http://api.semanticscholar.org/)

* [shibuya 3d](https://3dcel.com/study/case01/)

* [Stanford Large Network Dataset Collection](http://snap.stanford.edu/data/)



## experiments



## python

* neworkx

* plyfile

* rdflib

* pygsp

* pydotplus

* graphviz

* pygraphviz(require `apt install graphviz graphviz-dev`)



## others

* [cytoscape](https://cytoscape.org/index.html)

* [FBX](https://www.autodesk.com/products/fbx/overview)

* graphviz

* [STL](https://en.wikipedia.org/wiki/STL_(file_format))



## neuroscience

* [Dale's principle](https://en.wikipedia.org/wiki/Dale%27s_principle)



## TDA

* Vietoris-Rips complex

* prsistent homology

* barcode

* Taken's theorem

* Janko Latschev's theorem



## others

* https://paperswithcode.com/area/graphs

* https://ai.facebook.com/blog/open-sourcing-pytorch-biggraph-for-faster-embeddings-of-extremely-large-graphs

* https://ai.googleblog.com/2019/05/moving-camera-moving-people-deep.html

* https://jian-tang.com/files/AAAI19/aaai-grltutorial-part0-intro.pdf

* http://i.stanford.edu/~jure/pub/talks2/graph_gen-iclr-may19-long.pdf

* https://cs.stanford.edu/~jure/

*

### for Japanese

* https://www.slideshare.net/shotarosano5/automl-in-neurips-2018

* https://medium.com/programming-soda/graph-neural-network%E3%81%AE%E5%87%A6%E7%90%86%E3%81%A8%E5%8A%B9%E6%9E%9C%E3%82%92%E7%90%86%E8%A7%A3%E3%81%99%E3%82%8B-how-powerful-are-graph-neural-networks-a26ee9245cce 

* https://qiita.com/no_more_syakai/items/f1358e33e8376ae1766d

* https://www.slideshare.net/emakryo/neural-networks-for-graph-data-neurips2018pfn

* https://speakerdeck.com/m_mochizuki/ai-drug-discovery-in-the-view-of-competitions 

* https://speakerdeck.com/nnchiba/point-cloud-deep-learning-survey-ver-2

* https://engineer.dena.jp/2019/06/cv-papers-19-3dvision.html