Strongly and Weakly Augmented Graph Contrastive Learning Model for Molecular Property Prediction

Strongly and Weakly Augmented Graph Contrastive Learning Model for Molecular Property Prediction | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 6 May 2025 V1 Latest version Share on Strongly and Weakly Augmented Graph Contrastive Learning Model for Molecular Property Prediction Authors : Hui Du , Xing Zhang 0009-0005-2625-8426 [email protected] , Yimeng Zhang , Shihao Ji , Dongsheng Ma , and Xiaoli Wang Authors Info & Affiliations https://doi.org/10.22541/au.174650292.22127774/v1 239 views 105 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract In recent years, molecular property prediction methods based on graph neural networks have demonstrated significant advantages by modeling molecules as graph structures and leveraging their powerful feature extraction capabilities. However, since acquiring molecular label data typically relies on time-consuming and expensive experimental validation, data scarcity has become a major bottleneck limiting the further improvement of model performance. The emergence of graph contrastive learning offers a promising solution to this challenge. By pre-training on unlabeled datasets, graph contrastive learning can learn discriminative molecular representations, thereby mitigating the issue of insufficient labeled data. Nevertheless, due to the unique characteristics of molecular data, data augmentation may introduce semantic drift or impair the model’s generalization ability. To address this, we propose a Strongly and Weakly Augmented Graph Contrastive Learning model for Molecular Property Prediction (SWA-GCMPP), which aims to enhance the model’s generalization ability while preserving molecular semantic information. Specifically, SWA-GCMPP introduces two types of augmented views: a weakly augmented view and a strongly augmented view. The weakly augmented view utilizes a trainable topology augmenter to generate molecular graphs that preserve the molecule’s core topological structure, ensuring robust semantic consistency for contrastive learning. In contrast, the strongly augmented view applies four distinct graph augmentation strategies to introduce diverse structural variations, thereby improving the model’s generalization capability. Comprehensive experiments conducted on multiple molecular datasets from MoleculeNet demonstrate the effectiveness of SWA-GCMPP in molecular property prediction. Supplementary Material File (strongly_and_weakly_augmented_graph_contrastive_learning_model_for_molecular_property_prediction.pdf) Download 6.58 MB Information & Authors Information Version history V1 Version 1 06 May 2025 Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords data augmentation deep learning graph contrastive learning molecular property prediction Authors Affiliations Hui Du Northwest Normal University View all articles by this author Xing Zhang 0009-0005-2625-8426 [email protected] Northwest Normal University View all articles by this author Yimeng Zhang Northwest Normal University View all articles by this author Shihao Ji Northwest Normal University View all articles by this author Dongsheng Ma Northwest Normal University View all articles by this author Xiaoli Wang Xidian University View all articles by this author Metrics & Citations Metrics Article Usage 239 views 105 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Hui Du, Xing Zhang, Yimeng Zhang, et al. Strongly and Weakly Augmented Graph Contrastive Learning Model for Molecular Property Prediction. Authorea . 06 May 2025. DOI: https://doi.org/10.22541/au.174650292.22127774/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.174650292.22127774/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9ffc9ef3e93edf94',t:'MTc3OTQ2MTI5Nw=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();