├── GNN.jpg ├── README.md └── 第5章第6章コード.ipynb /GNN.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/atarum/GraphNeuralNetworks/5b9f9cda93355719f85cf519b1d305cff4fc080a/GNN.jpg -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 「グラフニューラルネットワーク」(オーム社) サポートページ 2 | [![グラフニューラルネットワーク](/GNN.jpg)](https://www.amazon.co.jp/dp/4274228878/) 3 | 4 | 「グラフニューラルネットワーク」(オーム社)に関するサポート情報を掲載します。 5 | ## 出版社・アマゾン
6 | オーム社 https://www.ohmsha.co.jp/book/9784274228872/
7 | アマゾン https://www.amazon.co.jp/dp/4274228878/
8 | 9 | ## 書誌情報
10 | グラフニューラルネットワーク: PyTorchによる実装
11 | 村田 剛志 著
12 | 本体3,200円+税
13 | A5判/248頁
14 | ISBN:978-4-274-22887-2
15 | 発売日:2022/07/20
16 | 発行元:オーム社
17 | 18 | ## 第5章第6章のコード 19 | - [このGitHub上で見る](/第5章第6章コード.ipynb "第5章第6章コード") 20 | - [Colaboratoryで見る](https://colab.research.google.com/drive/10MUzKFoYTQzelmmEwkPLNeo7PZu2G7pS?usp=sharing "Colaboratoryコード") 21 | 22 | ## 文中のリンク 23 | ### 第1章 グラフニューラルネットワークとは 24 | - 13ページ 25 | "Graph Neural Networks: A Review of Methods and Applications" 26 | Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun 27 | AI Open, Vol. 1, pp.57-81, 2020. 28 | https://doi.org/10.1016/j.aiopen.2021.01.001 29 | 30 | - 14ページ 31 | Traffic prediction with advanced Graph Neural Networks 32 | DeepMind, September 3, 2020. 33 | https://www.deepmind.com/blog/traffic-prediction-with-advanced-graph-neural-networks 34 | 35 | - 17ページ 36 | Graph Methods for COVID-19 Response 37 | William L. Hamilton 38 | https://cs.mcgill.ca/~wlh/comp766/files/graphs-against-covid.pdf 39 | 40 | ### 第2章 グラフエンベディング 41 | - 23ページ 42 | A Survey on Network Embedding 43 | Peng Cui, Xiao Wang, Jian Pei, Wenwu Zhu 44 | IEEE Transactions on Knowledge and Data Engineering, Vol. 31, No. 5, pp. 833-852, 2019. 45 | https://doi.org/10.1109/TKDE.2018.2849727 46 | 47 | - 31ページ 48 | DeepWalk: online learning of social representations 49 | Bryan Perozzi, Rami Al-Rfou, Steven Skiena 50 | The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'14), pp.701-710, 2014. 51 | https://doi.org/10.1145/2623330.2623732 52 | 著者Perozziによるコード 53 | https://github.com/phanein/deepwalk 54 | paperswithcode.comにおけるサイト 55 | https://paperswithcode.com/method/deepwalk 56 | 57 | - 36ページ 58 | LINE: Large-scale Information Network Embedding 59 | Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Qiaozhu Mei 60 | Proceedings of the 24th International Conference on World Wide Web (WWW'15) pp.1067-1077, 2015. 61 | https://doi.org/10.1145/2736277.2741093 62 | 著者Tangによるコード 63 | https://github.com/tangjianpku/LINE 64 | paperswithcode.comにおけるサイト 65 | https://paperswithcode.com/method/line 66 | 67 | - 39ページ 68 | node2vec: Scalable Feature Learning for Networks 69 | Aditya Grover, Jure Leskovec 70 | Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16) pp.855-864, 2016. 71 | https://doi.org/10.1145/2939672.2939754 72 | 著者Groverらによるサイト 73 | https://snap.stanford.edu/node2vec/ 74 | paperswithcode.comにおけるサイト 75 | https://paperswithcode.com/method/node2vec 76 | 77 | - 40ページ 78 | GraRep: Learning Graph Representations with Global Structural Information 79 | Shaosheng Cao, Wei Lu, Qiongkai Xu 80 | Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM'15) pp.891-900, 2015. 81 | https://doi.org/10.1145/2806416.2806512 82 | paperswithcode.comにおけるサイト 83 | https://paperswithcode.com/paper/grarep-learning-graph-representations-with 84 | 85 | - 44ページ 86 | グラフエンベディング手法の比較のためのPythonコード 87 | https://github.com/yijiaozhang/hypercompare 88 | 89 | ### 第3章 グラフにおける畳み込み 90 | - 60ページ 91 | Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering 92 | Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst 93 | Advances in Neural Information Processing Systems 29 (NIPS 2016), 2016. 94 | https://papers.nips.cc/paper/6081-convolutional-neural-networks-on-graphs-with-fast-localized-spectral-filtering 95 | https://arxiv.org/abs/1606.09375 96 | 著者Defferrardによるコード 97 | https://github.com/mdeff/cnn_graph 98 | paperswithcode.comにおけるサイト 99 | https://paperswithcode.com/paper/convolutional-neural-networks-on-graphs-with 100 | 101 | - 62ページ 102 | Semi-Supervised Classification with Graph Convolutional Networks 103 | Thomas N. Kipf, Max Welling 104 | 5th International Conference on Learning Representations (ICLR 2017), 2017. 105 | https://arxiv.org/abs/1609.02907 106 | 著者Kipfによるコード 107 | https://github.com/tkipf/gcn 108 | 著者Kipfによるサイト 109 | http://tkipf.github.io/graph-convolutional-networks/ 110 | 111 | - 65ページ 112 | Learning Convolutional Neural Networks for Graphs 113 | Mathias Niepert, Mohamed Ahmed, Konstantin Kutzkov 114 | Proceedings of the 33rd International Conference on Machine Learning (ICML 2016), 2016. 115 | https://arxiv.org/abs/1605.05273 116 | コード 117 | https://github.com/Lookuz/PATCHY-SAN 118 | paperswithcode.comにおけるサイト 119 | https://paperswithcode.com/paper/learning-convolutional-neural-networks-for 120 | 121 | - 67ページ 122 | Diffusion-Convolutional Neural Networks 123 | James Atwood, Don Towsley 124 | Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS 2016), 2016. 125 | https://arxiv.org/abs/1511.02136 126 | コード 127 | https://github.com/jcatw/dcnn 128 | paperswithcode.comにおけるサイト 129 | https://paperswithcode.com/paper/diffusion-convolutional-neural-networks 130 | 131 | - 69ページ 132 | Inductive Representation Learning on Large Graphs 133 | William L. Hamilton, Rex Ying, Jure Leskovec 134 | Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017), 2017. 135 | https://arxiv.org/abs/1706.02216 136 | コード 137 | https://github.com/williamleif/GraphSAGE 138 | 著者Hamiltonらによるサイト 139 | http://snap.stanford.edu/graphsage/ 140 | paperswithcode.comにおけるサイト 141 | https://paperswithcode.com/paper/inductive-representation-learning-on-large 142 | 143 | ### 第4章 関連トピック 144 | - 74ページ 145 | Structural Deep Network Embedding 146 | Daixin Wang, Peng Cui, Wenwu Zhu 147 | Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16), pp.1225–1234, 2016 148 | https://doi.org/10.1145/2939672.2939753 149 | paperswithcode.comにおけるサイト 150 | https://paperswithcode.com/paper/structural-deep-network-embedding 151 | 152 | - 80ページ 153 | Graph Attention Networks 154 | Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio 155 | 6th International Conference on Learning Representations (ICLR 2018), 2018. 156 | https://arxiv.org/abs/1710.10903 157 | コード 158 | https://github.com/PetarV-/GAT 159 | 著者Velickovicらによるサイト 160 | https://petar-v.com/GAT/ 161 | paperswithcode.comにおけるサイト 162 | https://paperswithcode.com/paper/graph-attention-networks 163 | 164 | - 83ページ 165 | Simplifying Graph Convolutional Networks 166 | Felix Wu, Tianyi Zhang, Amauri Holanda de Souza Jr., Christopher Fifty, Tao Yu, Kilian Q. Weinberger 167 | Proceedings of the 36th International Conference on Machine Learning (ICML 2019), 2019. 168 | https://arxiv.org/abs/1902.07153 169 | コード 170 | https://github.com/Tiiiger/SGC 171 | paperswithcode.comにおけるサイト 172 | https://paperswithcode.com/paper/simplifying-graph-convolutional-networks/ 173 | 174 | - 86ページ 175 | How Powerful are Graph Neural Networks? 176 | Keyulu Xu, Weihua Hu, Jure Leskovec, Stefanie Jegelka 177 | 7th International Conference on Learning Representations (ICLR 2019), 2019. 178 | https://arxiv.org/abs/1810.00826 179 | コード 180 | https://github.com/weihua916/powerful-gnns 181 | 182 | - 87ページ 183 | paperswithcode.comにおけるサイト 184 | https://paperswithcode.com/paper/how-powerful-are-graph-neural-networks/ 185 | A Survey on The Expressive Power of Graph Neural Networks 186 | Ryoma Sato 187 | https://arxiv.org/abs/2003.04078 188 | 189 | - 88ページ 190 | Adversarial Attacks and Defenses on Graphs 191 | Wei Jin, Yaxing Li, Han Xu, Yiqi Wang, Shuiwang Ji, Charu Aggarwal, Jiliang Tang 192 | ACM SIGKDD Explorations Newsletter, Vol.22, Issue 2, pp.19–34, 2020. 193 | https://doi.org/10.1145/3447556.3447566 194 | 195 | - 89ページ 196 | DeepRobust 197 | https://github.com/DSE-MSU/DeepRobust 198 | 199 | - 96ページ 200 | Explainability in Graph Neural Networks: A Taxonomic Survey 201 | Hao Yuan, Haiyang Yu, Shurui Gui, Shuiwang Ji 202 | https://arxiv.org/abs/2012.15445 203 | 204 | ### 第5章 実装のための準備 205 | - 103ページ 206 | Pythonの本家のサイト 207 | https://www.python.org/ 208 | Python情報サイト 209 | https://www.python.jp/ 210 | 211 | - 106ページ 212 | NumPyのquickstartのサイト 213 | https://numpy.org/doc/stable/user/quickstart.html 214 | 215 | - 109ページ 216 | SciPyのドキュメンテーション 217 | https://docs.scipy.org/doc/scipy/index.html 218 | 219 | - 112ページ 220 | pandasのドキュメンテーション 221 | https://pandas.pydata.org/docs/index.html 222 | 223 | - 113ページ 224 | Matplotlibの例 225 | https://matplotlib.org/stable/gallery/index.html 226 | 227 | - 115ページ 228 | Matplotlibのサイト 229 | https://matplotlib.org/stable/index.html 230 | 231 | - 116ページ 232 | seabornの例 233 | https://seaborn.pydata.org/examples/index.html 234 | 235 | - 117ページ 236 | seaborn.jointplot 237 | https://seaborn.pydata.org/generated/seaborn.jointplot.html 238 | 239 | - 118ページ 240 | seabornのサイト 241 | https://seaborn.pydata.org/ 242 | 243 | - 119ページ 244 | scikit-learnのサイト 245 | https://scikit-learn.org/stable/ 246 | 247 | - 120ページ 248 | scikit-learn algorithm cheat-sheet 249 | https://scikit-learn.org/stable/tutorial/machine_learning_map/ 250 | 251 | - 122ページ 252 | Laurens van der Maatenによるサイト(t-SNE) 253 | https://lvdmaaten.github.io/tsne/ 254 | 255 | - 123ページ 256 | How to use t-SNE Effectively 257 | https://distill.pub/2016/misread-tsne/ 258 | 259 | - 125ページ 260 | Scipy Lecture Notes (英語) 261 | https://scipy-lectures.org/ 262 | Scipy Lecture Notes (日本語訳) 263 | http://www.turbare.net/transl/scipy-lecture-notes/ 264 | 265 | - 126ページ 266 | Jupyter Notebook 267 | https://jupyter.org/ 268 | Anaconda 269 | https://www.anaconda.com/ 270 | 271 | - 127ページ 272 | JupyterLab Desktop App 273 | https://github.com/jupyterlab/jupyterlab-desktop 274 | 275 | - 128ページ 276 | Colaboratory 277 | https://colab.research.google.com/ 278 | 279 | ### 第6章 PyTorch Geometricによる実装 280 | - 135ページ 281 | PyTorch Get Started 282 | https://pytorch.org/get-started/locally/ 283 | Colab Notebooks and Video Tutorials 284 | https://pytorch-geometric.readthedocs.io/en/latest/notes/colabs.html 285 | 286 | - 136ページ 287 | PyTorchチュートリアル(日本語翻訳版) 288 | https://yutaroogawa.github.io/pytorch_tutorials_jp/ 289 | PyTorch Tutorials 290 | https://pytorch.org/tutorials/ 291 | PyTorch Documentation 292 | https://pytorch.org/docs/stable/ 293 | PyTorch basics (PyTorch Geometric Tutorial) 294 | https://antoniolonga.github.io/Pytorch_geometric_tutorials/posts/post2.html 295 | 296 | - 147ページ 297 | Loss Functions (PyTorch) 298 | https://pytorch.org/docs/stable/nn.html#loss-functions 299 | 300 | - 159ページ 301 | PyTorch Tutorials 302 | https://pytorch.org/tutorials/ 303 | PyTorchチュートリアル(日本語翻訳版) 304 | https://yutaroogawa.github.io/pytorch_tutorials_jp/ 305 | 306 | - 160ページ 307 | PyTorch Geometric (PyG) 308 | https://github.com/pyg-team/pytorch_geometric 309 | Deeo Graph Library (DGL) 310 | https://www.dgl.ai/ 311 | 312 | - 161ページ 313 | Graph Nets 314 | https://github.com/deepmind/graph_nets 315 | 316 | - 162ページ 317 | Lightning 318 | https://www.pytorchlightning.ai/ 319 | catalyst 320 | https://github.com/catalyst-team/catalyst 321 | fastai 322 | https://docs.fast.ai/ 323 | ignite 324 | https://github.com/pytorch/ignite 325 | 326 | - 163ページ 327 | Introduction by Example (PyG Documentation) 328 | https://pytorch-geometric.readthedocs.io/en/latest/notes/introduction.html 329 | 330 | - 167ページ 331 | TUDataset 332 | http://graphkernels.cs.tu-dortmund.de 333 | 334 | - 177ページ 335 | Colab Notebooks and Video Tutorials 336 | https://pytorch-geometric.readthedocs.io/en/latest/notes/colabs.html 337 | 338 | ### 第7章 今後の学習に向けて 339 | - 214ページ 340 | Introduction to Graph Neural Networks 341 | Zhiyuan Liu, Jie Zhou 342 | Morgan & Claypool Publishers, 2020. 343 | https://doi.org/10.2200/S00980ED1V01Y202001AIM045 344 | Graph Representation Learning 345 | William L. Hamilton 346 | Morgan & Claypool publishers, 2020. 347 | https://doi.org/10.2200/S01045ED1V01Y202009AIM046 348 | (preprint) 349 | https://www.cs.mcgill.ca/~wlh/grl_book/ 350 | 351 | - 215ページ 352 | Deep Learning on Graphs 353 | Yao Ma, Jiliang Tang 354 | Cambridge University Press, 2021. 355 | https://doi.org/10.1017/9781108924184 356 | (preprint) 357 | https://web.njit.edu/~ym329/dlg_book/ 358 | Graph Neural Networks -- Foundations, Frontiers, and Applications 359 | Lingfei Wu, Peng Cui, Jian Pei, Liang Zhao 360 | Springer, 2022. 361 | https://doi.org/10.1007/978-981-16-6054-2 362 | (preprint) 363 | https://graph-neural-networks.github.io/ 364 | 365 | - 216ページ 366 | A Comprehensive Survey on Graph Neural Networks 367 | Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu 368 | IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, Issue 1, pp.4-24, 2021. 369 | https://doi.org/10.1109/TNNLS.2020.2978386 370 | 371 | - 217ページ 372 | Graph Neural Networks: A Review of Methods and Applications 373 | Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun 374 | AI Open, Vol. 1, pp.57-81, 2020. 375 | https://doi.org/10.1016/j.aiopen.2021.01.001 376 | Deep Learning on Graphs: A Survey 377 | Ziwei Zhang, Peng Cui, Wenwu Zhu 378 | IEEE Transactions on Knowledge and Data Engineering, Vol. 34, pp. 249-270, 2022. 379 | https://doi.org/10.1109/TKDE.2020.2981333 380 | 381 | - 218ページ 382 | CS224W: Machine Learning with Graphs 383 | Stanford / Fall 2022 384 | http://web.stanford.edu/class/cs224w/ 385 | Pytorch Geometric Tutorial 386 | Antonio Longa, Gabriele Santin, Giovanni Pellegrini 387 | https://antoniolonga.github.io/Pytorch_geometric_tutorials/ 388 | Colab Notebooks and Video Tutorials 389 | https://pytorch-geometric.readthedocs.io/en/latest/notes/colabs.html 390 | 391 | - 219ページ 392 | Graph Neural Networks 393 | https://hhaji.github.io/Deep-Learning/Graph-Neural-Networks/ 394 | Must-read papers on GNN 395 | https://github.com/thunlp/GNNPapers 396 | Papers with codes – Graphs 397 | https://paperswithcode.com/area/graphs 398 | Awesome resources on Graph Neural Networks 399 | https://github.com/GRAND-Lab/Awesome-Graph-Neural-Networks 400 | 401 | - 220ページ 402 | Open Graph Benchmark (OGB) 403 | https://ogb.stanford.edu/ 404 | --------------------------------------------------------------------------------