{"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-message-passing-for-quantum-chemistry","title":"Neural Message Passing for Quantum Chemistry","arxiv_id":"1704.01212","date":"2017-04-04","proceeding":"ICML 2017 8","authors":["Justin Gilmer","Samuel S. Schoenholz","Patrick F. Riley","Oriol Vinyals","George E. Dahl"],"abstract":"Supervised learning on molecules has incredible potential to be useful in\nchemistry, drug discovery, and materials science. Luckily, several promising\nand closely related neural network models invariant to molecular symmetries\nhave already been described in the literature. These models learn a message\npassing algorithm and aggregation procedure to compute a function of their\nentire input graph. At this point, the next step is to find a particularly\neffective variant of this general approach and apply it to chemical prediction\nbenchmarks until we either solve them or reach the limits of the approach. In\nthis paper, we reformulate existing models into a single common framework we\ncall Message Passing Neural Networks (MPNNs) and explore additional novel\nvariations within this framework. Using MPNNs we demonstrate state of the art\nresults on an important molecular property prediction benchmark; these results\nare strong enough that we believe future work should focus on datasets with\nlarger molecules or more accurate ground truth labels.","url_abs":"http://arxiv.org/abs/1704.01212v2","url_pdf":"http://arxiv.org/pdf/1704.01212v2.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-message-passing-for-quantum-chemistry","repo_url":"https://github.com/brain-research/mpnn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/AJS1NGH/Predicting-Molecular-Properties-Challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/CoderPat/OpenGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/LRacoci/permutation-graphml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/MUmarJaved/MultiAgent-Distributed-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/Microsoft/gated-graph-neural-network-samples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/Samyu0304/thought-propagation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/Tony-Y/cgnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/cts198859/deeprl_dist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/cts198859/deeprl_network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/dongchen06/macacc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/fredjo89/heterogeneous-mpnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/gajeelSF/Reinforcement-Learning-Branch-and-Bound","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/nrel/m2p","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/priba/nmp_qc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/priba/siamese_ged","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/teddykoker/mpnn-for-quantum-chem","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/tomdbar/eco-dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/Saro00/DGN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"neural-message-passing-for-quantum-chemistry","repo_url":"https://github.com/lukecavabarrett/pna","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"formation-energy","task_name":"Formation Energy"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[{"method_slug":"gru","method_name":"GRU"},{"method_slug":"mpnn","method_name":"MPNN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"mpnn","name":"MPNN","full_name":"Message Passing Neural Network"}],"results":[{"leaderboard":"/sota/drug-discovery-on-qm9","task":"Drug Discovery","dataset":"QM9","model":"MPNNs","rank_in_archive_order":9,"of":11,"metrics":{"Error ratio":"0.68"},"uses_additional_data":false},{"leaderboard":"/sota/formation-energy-on-qm9","task":"Formation Energy","dataset":"QM9","model":"MPNN","rank_in_archive_order":17,"of":18,"metrics":{"MAE":"0.49"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-lipophilicity","task":"Graph Regression","dataset":"Lipophilicity","model":"MPNN","rank_in_archive_order":13,"of":23,"metrics":{"RMSE":"0.719"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-100k","task":"Graph Regression","dataset":"ZINC 100k","model":"MPNN","rank_in_archive_order":5,"of":8,"metrics":{"MAE":"0.288"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"MPNN (sum)","rank_in_archive_order":26,"of":36,"metrics":{"MAE":"0.145 "},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"MPNN (max)","rank_in_archive_order":29,"of":36,"metrics":{"MAE":"0.252"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-with-public","task":"Node Classification","dataset":"CiteSeer with Public Split: fixed 20 nodes per class","model":"MPNN","rank_in_archive_order":39,"of":40,"metrics":{"Accuracy":"64.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1704.01212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01212"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/Samyu0304/thought-propagation","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cts198859/deeprl_network","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gajeelSF/Reinforcement-Learning-Branch-and-Bound","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Saro00/DGN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MUmarJaved/MultiAgent-Distributed-Reinforcement-Learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/priba/siamese_ged","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fredjo89/heterogeneous-mpnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nrel/m2p","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CoderPat/OpenGNN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/priba/nmp_qc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/teddykoker/mpnn-for-quantum-chem","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dongchen06/macacc","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tomdbar/eco-dqn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LRacoci/permutation-graphml","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Tony-Y/cgnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/brain-research/mpnn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Microsoft/gated-graph-neural-network-samples","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AJS1NGH/Predicting-Molecular-Properties-Challenge","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cts198859/deeprl_dist","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukecavabarrett/pna","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"dd41a32952411206","entry":"create_dim_in","repo":"fredjo89/heterogeneous-mpnn","repo_kind":"listed","path":"models_HMPNN_ct.py","file_url":"https://github.com/fredjo89/heterogeneous-mpnn/blob/HEAD/models_HMPNN_ct.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd41a32952411206"}},{"code_sha256_prefix":"663130aa4f6e9397","entry":"feed_forward","repo":"teddykoker/mpnn-for-quantum-chem","repo_kind":"listed","path":"mpnn/model.py","file_url":"https://github.com/teddykoker/mpnn-for-quantum-chem/blob/HEAD/mpnn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"663130aa4f6e9397"}},{"code_sha256_prefix":"06ae24901264ad1a","entry":"restricted_float","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"06ae24901264ad1a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}