{"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/very-deep-graph-neural-networks-via-noise","title":"Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond","arxiv_id":"2106.07971","date":"2021-06-15","proceeding":null,"authors":["Jonathan Godwin","Michael Schaarschmidt","Alexander Gaunt","Alvaro Sanchez-Gonzalez","Yulia Rubanova","Petar Veličković","James Kirkpatrick","Peter Battaglia"],"abstract":"In this paper we show that simple noise regularisation can be an effective way to address GNN oversmoothing. First we argue that regularisers addressing oversmoothing should both penalise node latent similarity and encourage meaningful node representations. From this observation we derive \"Noisy Nodes\", a simple technique in which we corrupt the input graph with noise, and add a noise correcting node-level loss. The diverse node level loss encourages latent node diversity, and the denoising objective encourages graph manifold learning. Our regulariser applies well-studied methods in simple, straightforward ways which allow even generic architectures to overcome oversmoothing and achieve state of the art results on quantum chemistry tasks, and improve results significantly on Open Graph Benchmark (OGB) datasets. Our results suggest Noisy Nodes can serve as a complementary building block in the GNN toolkit.","url_abs":"https://arxiv.org/abs/2106.07971v2","url_pdf":"https://arxiv.org/pdf/2106.07971v2.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":"very-deep-graph-neural-networks-via-noise","repo_url":"https://github.com/Namkyeong/NoisyNodes_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"graph-property-prediction","task_name":"Graph Property Prediction"},{"task_slug":"initial-structure-to-relaxed-energy-is2re","task_name":"Initial Structure to Relaxed Energy (IS2RE)"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/initial-structure-to-relaxed-energy-is2re-on","task":"Initial Structure to Relaxed Energy (IS2RE)","dataset":"OC20","model":"Noisy Nodes","rank_in_archive_order":4,"of":4,"metrics":{"Energy MAE":"0.47225"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07971"}},"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/Namkyeong/NoisyNodes_Pytorch","reach":null}],"summary":{"ran":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"78dc845536deb618","entry":"GNBlock","repo":"Namkyeong/NoisyNodes_Pytorch","repo_kind":"listed","path":"embedder/graphnetwork.py","file_url":"https://github.com/Namkyeong/NoisyNodes_Pytorch/blob/HEAD/embedder/graphnetwork.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78dc845536deb618"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}