{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-relational-inference-for-interacting","title":"Neural Relational Inference for Interacting Systems","arxiv_id":"1802.04687","date":"2018-02-13","proceeding":"ICML 2018 7","authors":["Thomas Kipf","Ethan Fetaya","Kuan-Chieh Wang","Max Welling","Richard Zemel"],"abstract":"Interacting systems are prevalent in nature, from dynamical systems in\nphysics to complex societal dynamics. The interplay of components can give rise\nto complex behavior, which can often be explained using a simple model of the\nsystem's constituent parts. In this work, we introduce the neural relational\ninference (NRI) model: an unsupervised model that learns to infer interactions\nwhile simultaneously learning the dynamics purely from observational data. Our\nmodel takes the form of a variational auto-encoder, in which the latent code\nrepresents the underlying interaction graph and the reconstruction is based on\ngraph neural networks. In experiments on simulated physical systems, we show\nthat our NRI model can accurately recover ground-truth interactions in an\nunsupervised manner. We further demonstrate that we can find an interpretable\nstructure and predict complex dynamics in real motion capture and sports\ntracking data.","url_abs":"http://arxiv.org/abs/1802.04687v2","url_pdf":"http://arxiv.org/pdf/1802.04687v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/ethanfetaya/nri","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/ELEMKEP/bsc_lcs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/ipeter50/graph_ode","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/loeweX/AmortizedCausalDiscovery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/mariel-pettee/choreo-graph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/mitmul/chainer-nri","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/mkofinas/locs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/pairlab/v-cdn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-relational-inference-for-interacting","repo_url":"https://github.com/quizzicalkudu/curly-spork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.04687","atlas_url":"https://app.syntology.ai/?focus=1802.04687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04687"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/loeweX/AmortizedCausalDiscovery","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ELEMKEP/bsc_lcs","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ipeter50/graph_ode","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/quizzicalkudu/curly-spork","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mariel-pettee/choreo-graph","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ethanfetaya/nri","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mitmul/chainer-nri","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pairlab/v-cdn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mkofinas/locs","reach":null}],"summary":{"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":5,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"aac319f56fd6feff","entry":"get_sender_receiver","repo":"mitmul/chainer-nri","repo_kind":"listed","path":"utils/visualize_results.py","file_url":"https://github.com/mitmul/chainer-nri/blob/HEAD/utils/visualize_results.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aac319f56fd6feff"}},{"code_sha256_prefix":"a0bc850b6e4e06c3","entry":"binary_concrete","repo":"quizzicalkudu/curly-spork","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/quizzicalkudu/curly-spork/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0bc850b6e4e06c3"}},{"code_sha256_prefix":"827289450cb41f39","entry":"binary_concrete_sample","repo":"quizzicalkudu/curly-spork","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/quizzicalkudu/curly-spork/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"827289450cb41f39"}},{"code_sha256_prefix":"12d0d79170d76415","entry":"generate_dataset","repo":"ethanfetaya/nri","repo_kind":"official","path":"data/generate_dataset.py","file_url":"https://github.com/ethanfetaya/nri/blob/HEAD/data/generate_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12d0d79170d76415"}},{"code_sha256_prefix":"9310c1921882d972","entry":"my_softmax","repo":"quizzicalkudu/curly-spork","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/quizzicalkudu/curly-spork/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9310c1921882d972"}},{"code_sha256_prefix":"5de9491cb82f0f38","entry":"nll_gaussian","repo":"quizzicalkudu/curly-spork","repo_kind":"listed","path":"lstm_baseline.py","file_url":"https://github.com/quizzicalkudu/curly-spork/blob/HEAD/lstm_baseline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5de9491cb82f0f38"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}