{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/pre-training-graph-neural-networks-on","title":"Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck","arxiv_id":null,"date":"2025-02-20","proceeding":null,"authors":["Van Thuy Hoang; O-Joun Lee"],"abstract":"This study aims to build a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge. Although various attempts have been proposed to overcome limitations in acquiring labeled molecules, the previous pre-training methods still rely on semantic subgraphs, i.e., functional groups. Only focusing on the functional groups could overlook the graph-level distinctions. The key challenge to build a pre-trained GNN on molecules is how to (1) generate well-distinguished graph-level representations and (2) automatically discover the functional groups without prior knowledge. To solve it, we propose a novel Subgraph-conditioned Graph Information Bottleneck, named S-CGIB, for pre-training GNNs to recognize core subgraphs (graph cores) and significant subgraphs. The main idea is that the graph cores contain compressed and sufficient information that could generate well-distinguished graph-level representations and reconstruct the input graph conditioned on significant subgraphs across molecules under the S-CGIB principle. To discover significant subgraphs without prior knowledge about functional groups, we propose generating a set of functional group candidates, i.e., ego networks, and using an attention-based interaction between the graph core and the candidates. Despite being identified from self-supervised learning, our learned subgraphs match the real-world functional groups. Extensive experiments on molecule datasets across various domains demonstrate the superiority of S-CGIB.","url_abs":"https://arxiv.org/abs/2412.15589","url_pdf":"https://arxiv.org/pdf/2412.15589","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":"pre-training-graph-neural-networks-on","repo_url":"https://github.com/NSLab-CUK/S-CGIB","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-mutagenicity","task":"Graph Classification","dataset":"Mutagenicity","model":"S-CGIB","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"81.12±0.90"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"S-CGIB","rank_in_archive_order":39,"of":69,"metrics":{"Accuracy":"79.75±0.82"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci109","task":"Graph Classification","dataset":"NCI109","model":"S-CGIB","rank_in_archive_order":23,"of":38,"metrics":{"Accuracy":"77.54±1.51"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"S-CGIB","rank_in_archive_order":2,"of":20,"metrics":{"ROC-AUC":"86.46±0.81"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"S-CGIB","rank_in_archive_order":9,"of":29,"metrics":{"ROC-AUC":"88.75±0.49"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-esol","task":"Molecular Property Prediction","dataset":"ESOL","model":"S-CGIB","rank_in_archive_order":16,"of":20,"metrics":{"RMSE":"0.816±0.019"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","task":"Molecular Property Prediction","dataset":"FreeSolv","model":"S-CGIB","rank_in_archive_order":14,"of":22,"metrics":{"RMSE":"1.648±0.074"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-1","task":"Molecular Property Prediction","dataset":"HIV","model":"S-CGIB","rank_in_archive_order":4,"of":4,"metrics":{"ROC-AUC":"78.33±1.34"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on","task":"Molecular Property Prediction","dataset":"Lipophilicity","model":"S-CGIB","rank_in_archive_order":8,"of":13,"metrics":{"RMSE":"0.762±0.042"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-muv-1","task":"Molecular Property Prediction","dataset":"MUV","model":"S-CGIB","rank_in_archive_order":3,"of":5,"metrics":{"ROC-AUC":"77.71±1.19"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"S-CGIB","rank_in_archive_order":12,"of":19,"metrics":{"ROC-AUC":"64.03±1.04"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"S-CGIB","rank_in_archive_order":4,"of":20,"metrics":{"ROC-AUC":"80.94±0.17"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-toxcast-1","task":"Molecular Property Prediction","dataset":"ToxCast","model":"S-CGIB","rank_in_archive_order":2,"of":8,"metrics":{"ROC-AUC":"70.95±0.27"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"S-CGIB","rank_in_archive_order":13,"of":20,"metrics":{"ROC-AUC":"78.58±2.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"NSLab-CUK/S-CGIB","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2412.15589"],"harvested_for_calls":[{"arxiv_id":"2412.15589","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.15589"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.15589\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7267833e95ca320001bcba5be0e145ae1d7b72f49a61e5cd42f5ca18c435ba82","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}