{"id":13689439,"url":"https://github.com/mitmul/chainer-nri","last_synced_at":"2025-03-23T15:31:37.427Z","repository":{"id":141384881,"uuid":"167088434","full_name":"mitmul/chainer-nri","owner":"mitmul","description":"Reproduction work of \"Neural Relational Inference for Interacting Systems\" in Chainer","archived":false,"fork":false,"pushed_at":"2019-02-05T03:46:55.000Z","size":1110,"stargazers_count":32,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-18T21:54:31.321Z","etag":null,"topics":["chainer","deep-learning","graph-neural-networks"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mitmul.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-01-23T00:20:56.000Z","updated_at":"2024-05-31T07:44:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"4ef57035-578e-4099-900c-b3310550ccd2","html_url":"https://github.com/mitmul/chainer-nri","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fchainer-nri","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fchainer-nri/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fchainer-nri/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fchainer-nri/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mitmul","download_url":"https://codeload.github.com/mitmul/chainer-nri/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245122859,"owners_count":20564395,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chainer","deep-learning","graph-neural-networks"],"created_at":"2024-08-02T15:01:47.972Z","updated_at":"2025-03-23T15:31:37.412Z","avatar_url":"https://github.com/mitmul.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Neural Relational Inference (NRI)\n\n**Graph Neural Network for interacting systems**\n\n![](images/result.gif)\n\nGiven a time series data of nodes, the NRI model predicts the future node states and underlying relashionship between the nodes as edges.\n\nThis is a reproduction work of the neural relational inference (NRI) in Chainer. The original implementation by the authors is found here: [ethanfetaya/NRI](https://github.com/ethanfetaya/NRI).\n\nPlease refer for details to the paper:\u003cbr /\u003e\n**Neural relational inference for interacting systems.**\u003cbr /\u003e\nThomas Kipf*, Ethan Fetaya*, Kuan-Chieh Wang, Max Welling, Richard Zemel.\u003cbr /\u003e\nhttps://arxiv.org/abs/1802.04687 (*: equal contribution)\u003cbr /\u003e\n\n## Dataset\n\n### Particle Physics Simulation Dataset\n\n```bash\ncd data\npython generate_dataset.py\n```\n\n## Training\n\n### Particle Physics Simulation Dataset\n\n```bash\npython train.py --gpu 0\n```\n\n## Visualize results\n\n```bash\npython utils/visualize_results.py \\\n--args-file results/2019-01-22_10-20-25_0/args.json \\\n--encoder-snapshot results/2019-01-22_10-20-25_0/encoder_epoch-500.npz \\\n--decoder-snapshot results/2019-01-22_10-20-25_0/decoder_epoch-500.npz \\\n--gpu 0\n```\n\n## Quantitative evaluation\n\n### Accuracy (in %) of unsupervised interaction recovery\n\n| Model                                  | Springs - 5 nodes (test) |\n|:---------------------------------------|:-------------------------|\n| chainer-nri (MLPEncoder, MLPDecoder)   | 99.8                     |\n| chainer-nri (CNNEncoder, MLPDecoder)   | 99.4                     |\n| Original (from paper)                  | 99.9                     |\n\n### Mean squared error (MSE) in predicting future states for simulations with 5 nodes\n\n| Model                                  | Springs - 5 nodes (test) |\n|:---------------------------------------|:-------------------------|\n| chainer-nri (MLPEncoder, MLPDecoder)   | 3.75e-05                 |\n| chainer-nri (CNNEncoder, MLPDecoder)   | 3.83e-05                 |\n| Original (from paper)                  | 3.12e-08                 |","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmitmul%2Fchainer-nri","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmitmul%2Fchainer-nri","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmitmul%2Fchainer-nri/lists"}