Knowledge engineering: from people to machines and back
Graph deep learningまとめ (as of 20190919)
1. Graph deep learning
aka geometric deep learning
(as of 20190919)
, Review papers
workshop
Representation learning on irregularly structured input
data such as graphs, point clouds, and manifolds
6. 1. Geometric deep learning: going beyond Euclidean data
(Bronstein+ IEEE Signal Processing Magazine, 2017)
https://doi.org/10.1109/MSP.2017.2693418
2. Representation Learning on Graphs: Methods and Applications
(Halilton+ IEEE Data Engineering Bulletin, 2017)
http://sites.computer.org/debull/A17sept/p52.pdf
3. Graph embedding techniques, applications, and performance: A survey
(Goyal+ Knowledge-Based Systems, 2018)
https://doi.org/10.1016/j.knosys.2018.03.022
4. Relational inductive biases, deep learning, and graph networks
(Battaglia+ arXiv:1806.01261, 2018)
https://arxiv.org/abs/1806.01261
5. Deep Learning on Graphs: A Survey
(Zhang+ arXiv:1812.04202, 2018)
https://arxiv.org/abs/1812.04202
6. Attention Models in Graphs: A Survey
(Lee+ arXiv:1807.07984, 2018)
https://arxiv.org/abs/1807.07984
7. A comprehensive survey on graph neural networks
(Wu+ arXiv:1901.00596, 2019)
https://arxiv.org/abs/1901.00596
8. Graph Neural Networks: A Review of Methods and Applications
(Zhou+ arXiv:1812.08434 , 2019)
https://arxiv.org/abs/1812.08434
(review papers)
7. Websites/Workshops
• NeurIPS2019 Workshop on Graph Representation Learning
https://grlearning.github.io/
• ICLR2019 Workshop on Representation Learning on Graphs and Manifolds (RLGM)
https://rlgm.github.io/overview/
• ICML2019 Workshop on Learning and Reasoning with Graph-Structured Representations
https://graphreason.github.io
• KDD2019 Workshop on Mining and Learning with Graphs (MLG)
http://www.mlgworkshop.org/2019/
• KDD2019 Workshop on Deep Learning on Graphs (DLG)
https://dlg2019.bitbucket.io
• SDM2019 Workshop on Deep Learning on Graphs
https://sites.google.com/view/graph-representation-workshop/
• Tutorials (geometricdeeplearning.com)
http://geometricdeeplearning.com/#portfolio
• Dive into Deep Learning
https://www.d2l.ai
• Practical Deep Learning for Coders
https://course.fast.ai
• Interpretable Machine Learning
https://christophm.github.io/interpretable-ml-book/
Online books (not graph-speci c)
8. List of papers ( )
• http://geometricdeeplearning.com/#bibliography
• https://paperswithcode.com/task/graph-neural-network
• Literature of Deep Learning for Graphs
https://github.com/DeepGraphLearning/LiteratureDL4Graph
• Awesome resources on Graph Neural Networks
https://github.com/nnzhan/Awesome-Graph-Neural-Networks
• Awesome Graph Classification
https://github.com/benedekrozemberczki/awesome-graph-classification
• Must-read papers on GNN
https://github.com/thunlp/GNNPapers
SOTA
• Browse > Graphs
https://paperswithcode.com/area/graphs
• Browse > Graphs > Graph Classification
https://paperswithcode.com/task/graph-classification
paperswithcode.com
9. Graph Nets library
https://github.com/deepmind/graph_nets
Pytorch geometric
https://github.com/rusty1s/pytorch_geometric
Deep Graph Library (DGL)
https://github.com/dmlc/dgl
Libraries/Frameworks
Chainer Chemistry
https://github.com/pfnet-research/chainer-chemistry
Kaggle:
• CHAMPS (CHemistry And Mathematics in Phase Space) competition
https://www.kaggle.com/c/champs-scalar-coupling/overview
• #1 Solution - hybrid
https://www.kaggle.com/c/champs-scalar-coupling/discussion/106575#latest-628267
• #2 solution 🤖 Quantum Uncertainty 🤖
https://www.kaggle.com/c/champs-scalar-coupling/discussion/106468#latest-618474
• 3rd solution - BERT in chemistry - End to End is all you need
https://www.kaggle.com/c/champs-scalar-coupling/discussion/106572#latest-620382