{
  "id": 61461,
  "title": "[pytorch] Deep message passing network using Graph RNN",
  "url": "/competitions/trackml-particle-identification/discussion/61461",
  "author_name": "hengck23",
  "post_date": "2018-07-19T17:30:24.585000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>For your reference:</p>\n\n<p>ideas from:</p>\n\n<p>-\n <a href=\"https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\">https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf</a></p>\n\n<ul>\n<li><p>\"High-Precision Automated Reconstruction of Neurons with Flood-Filling Networks\" - Nature 2018 <a href=\"https://ai.googleblog.com/2018/07/improving-connectomics-by-order-of.html\">https://ai.googleblog.com/2018/07/improving-connectomics-by-order-of.html</a></p></li>\n<li><p>\"Neural relational inference for interacting systems\" - ICML 2018\n<a href=\"https://github.com/ethanfetaya/nri\">https://github.com/ethanfetaya/nri</a></p></li>\n<li><p>\"Neural Message Passing for Quantum Chemistry\" - ICML 2017\n<a href=\"https://github.com/priba/nmp_qc\">https://github.com/priba/nmp_qc</a></p></li>\n</ul>\n\n<hr>\n\n<p>results of some training iterations:</p>\n\n<p>input is pairwise link constrained by geometry (e.g. distance of hit pairs &lt; threshold).</p>\n\n<p>Black: ground truth, Red: results of graph RNN </p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9930/iter00.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9931/iter01.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9929/iter02.png\" alt=\"enter image description here\"></p>\n\n<p>pytorch code as attached:</p>",
  "messages": [
    {
      "id": 359226,
      "postDate": "2018-07-19T17:30:24.587Z",
      "content": "<p>For your reference:</p>\n\n<p>ideas from:</p>\n\n<p>-\n <a href=\"https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\">https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf</a></p>\n\n<ul>\n<li><p>\"High-Precision Automated Reconstruction of Neurons with Flood-Filling Networks\" - Nature 2018 <a href=\"https://ai.googleblog.com/2018/07/improving-connectomics-by-order-of.html\">https://ai.googleblog.com/2018/07/improving-connectomics-by-order-of.html</a></p></li>\n<li><p>\"Neural relational inference for interacting systems\" - ICML 2018\n<a href=\"https://github.com/ethanfetaya/nri\">https://github.com/ethanfetaya/nri</a></p></li>\n<li><p>\"Neural Message Passing for Quantum Chemistry\" - ICML 2017\n<a href=\"https://github.com/priba/nmp_qc\">https://github.com/priba/nmp_qc</a></p></li>\n</ul>\n\n<hr>\n\n<p>results of some training iterations:</p>\n\n<p>input is pairwise link constrained by geometry (e.g. distance of hit pairs &lt; threshold).</p>\n\n<p>Black: ground truth, Red: results of graph RNN </p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9930/iter00.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9931/iter01.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9929/iter02.png\" alt=\"enter image description here\"></p>\n\n<p>pytorch code as attached:</p>",
      "rawMarkdown": "For your reference:\n\nideas from:\n\n\n -\n https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\n\n- \"High-Precision Automated Reconstruction of Neurons with Flood-Filling Networks\" - Nature 2018 https://ai.googleblog.com/2018/07/improving-connectomics-by-order-of.html\n\n\n\n-  \"Neural relational inference for interacting systems\" - ICML 2018\n https://github.com/ethanfetaya/nri\n\n- \"Neural Message Passing for Quantum Chemistry\" - ICML 2017\nhttps://github.com/priba/nmp_qc\n\n---\n\nresults of some training iterations:\n\ninput is pairwise link constrained by geometry (e.g. distance of hit pairs &lt; threshold).\n\nBlack: ground truth, Red: results of graph RNN \n\n\n  ![enter image description here][1]\n\n  ![enter image description here][2]\n\n  ![enter image description here][3]\n\n\npytorch code as attached:\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9930/iter00.png\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9931/iter01.png\n  [3]: https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9929/iter02.png",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "359226": "For your reference:\n\nideas from:\n\n\n -\n https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\n\n- \"High-Precision Automated Reconstruction of Neurons with Flood-Filling Networks\" - Nature 2018 https://ai.googleblog.com/2018/07/improving-connectomics-by-order-of.html\n\n\n\n-  \"Neural relational inference for interacting systems\" - ICML 2018\n https://github.com/ethanfetaya/nri\n\n- \"Neural Message Passing for Quantum Chemistry\" - ICML 2017\nhttps://github.com/priba/nmp_qc\n\n---\n\nresults of some training iterations:\n\ninput is pairwise link constrained by geometry (e.g. distance of hit pairs &lt; threshold).\n\nBlack: ground truth, Red: results of graph RNN \n\n\n  ![enter image description here][1]\n\n  ![enter image description here][2]\n\n  ![enter image description here][3]\n\n\npytorch code as attached:\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9930/iter00.png\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9931/iter01.png\n  [3]: https://storage.googleapis.com/kaggle-forum-message-attachments/359226/9929/iter02.png"
  }
}