{"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/graph-networks-as-a-universal-machine","title":"Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals","arxiv_id":"1812.05055","date":"2018-12-12","proceeding":null,"authors":["Chi Chen","Weike Ye","Yunxing Zuo","Chen Zheng","Shyue Ping Ong"],"abstract":"Graph networks are a new machine learning (ML) paradigm that supports both relational reasoning and combinatorial generalization. Here, we develop universal MatErials Graph Network (MEGNet) models for accurate property prediction in both molecules and crystals. We demonstrate that the MEGNet models outperform prior ML models such as the SchNet in 11 out of 13 properties of the QM9 molecule data set. Similarly, we show that MEGNet models trained on $\\sim 60,000$ crystals in the Materials Project substantially outperform prior ML models in the prediction of the formation energies, band gaps and elastic moduli of crystals, achieving better than DFT accuracy over a much larger data set. We present two new strategies to address data limitations common in materials science and chemistry. First, we demonstrate a physically-intuitive approach to unify four separate molecular MEGNet models for the internal energy at 0 K and room temperature, enthalpy and Gibbs free energy into a single free energy MEGNet model by incorporating the temperature, pressure and entropy as global state inputs. Second, we show that the learned element embeddings in MEGNet models encode periodic chemical trends and can be transfer-learned from a property model trained on a larger data set (formation energies) to improve property models with smaller amounts of data (band gaps and elastic moduli).","url_abs":"http://arxiv.org/abs/1812.05055v1","url_pdf":"http://arxiv.org/pdf/1812.05055v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"graph-networks-as-a-universal-machine","repo_url":"https://github.com/materialsvirtuallab/megnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"graph-networks-as-a-universal-machine","repo_url":"https://github.com/dcccc/LC_NET","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-networks-as-a-universal-machine","repo_url":"https://github.com/dcccc/git_python","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/formation-energy-on-materials-project","task":"Formation Energy","dataset":"Materials Project","model":"MEGNet","rank_in_archive_order":5,"of":9,"metrics":{"MAE":"28"},"uses_additional_data":false},{"leaderboard":"/sota/formation-energy-on-qm9","task":"Formation Energy","dataset":"QM9","model":"MEGNet-Full","rank_in_archive_order":11,"of":18,"metrics":{"MAE":"0.21"},"uses_additional_data":false},{"leaderboard":"/sota/formation-energy-on-qm9","task":"Formation Energy","dataset":"QM9","model":"MEGNet-simple","rank_in_archive_order":14,"of":18,"metrics":{"MAE":"0.28"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.05055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05055"}},"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/dcccc/LC_NET","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dcccc/git_python","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/materialsvirtuallab/megnet","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"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":"793d95f974b73be9","entry":"accuracy","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/utils/metrics.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"793d95f974b73be9"}},{"code_sha256_prefix":"4fc6585b7b5fce76","entry":"expand_1st","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/utils/general.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/utils/general.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4fc6585b7b5fce76"}},{"code_sha256_prefix":"44e79b9c39926ed4","entry":"fast_label_binarize","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/utils/general.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/utils/general.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"44e79b9c39926ed4"}},{"code_sha256_prefix":"7cd70353cde137d0","entry":"mae","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/utils/metrics.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7cd70353cde137d0"}},{"code_sha256_prefix":"310cd70b817b692c","entry":"mean_squared_error_with_scale","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/losses.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"310cd70b817b692c"}},{"code_sha256_prefix":"2e536987121d9a8e","entry":"repeat_with_index","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/utils/layer.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/utils/layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2e536987121d9a8e"}},{"code_sha256_prefix":"b72502cbc4652705","entry":"softplus2","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/activations.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/activations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b72502cbc4652705"}},{"code_sha256_prefix":"a66746c53f581f24","entry":"swish","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/activations.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/activations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a66746c53f581f24"}},{"code_sha256_prefix":"5b8cd0953f2acd70","entry":"to_list","repo":"materialsvirtuallab/megnet","repo_kind":"official","path":"megnet/utils/general.py","file_url":"https://github.com/materialsvirtuallab/megnet/blob/HEAD/megnet/utils/general.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5b8cd0953f2acd70"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}