[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119929-en":3,"doc-seo-119929-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119929,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","NeuroGraph - Benchmarks for Graph Machine Learning in Brain Connectomics","Machine learning enables effective analysis of high-dimensional functional neuroimaging data and supports prediction of neurological conditions, psychiatric disorders, and cognitive patterns. Functional MRI research often models brain-region interactions with graph representations, but applying graph machine learning is difficult due to numerous preprocessing pipelines and a large search space for graph construction. This paper presents NeuroGraph, a set of graph-based neuroimaging datasets, and evaluates graph learning across 35 generated datasets and 15+ baseline methods, covering static and dynamic connectivity. An open-source Python package supplies benchmarks, baselines, training, and standard evaluation.","NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics  \narXiv :2306 .06202v3 [ cs .LG] 22 Nov 2023  \nAnwar Said  \nVanderbilt University [anwar.said@vanderbilt.edu](anwar.said@vanderbilt.edu)  \nTyler Derr  \nVanderbilt University [tyler.derr@vanderbilt.edu](tyler.derr@vanderbilt.edu)  \nDaniel Moyer  \nVanderbilt University [daniel.moyer@vanderbilt.edu](daniel.moyer@vanderbilt.edu)  \nRoza G. Bayrak  \nVanderbilt University [roza.g.bayrak@vanderbilt.edu](roza.g.bayrak@vanderbilt.edu)  \nMudassir Shabbir  \nVanderbilt University Information Technology University [mudassir.shabbir@itu.edu.pk](mudassir.shabbir@itu.edu.pk)  \nCatie Chang  \nVanderbilt University [catie.chang@vanderbilt.edu](catie.chang@vanderbilt.edu)  \nXenofon Koutsoukos  \nVanderbilt University  \n[xenofon.koutsoukos@vanderbilt.edu](xenofon.koutsoukos@vanderbilt.edu)  \nAbstract  \nMachine learning provides a valuable tool for analyzing high-dimensional functional neuroimaging data, and is proving effective in predicting various neurological conditions, psychiatric disorders, and cognitive patterns. In functional magnetic resonance imaging (MRI) research, interactions between brain regions are commonly modeled using graph-based representations. The potency of graph machine learning methods has been established across myriad domains, marking a transformative step in data interpretation and predictive modeling. Yet, despite their promise, the transposition of these techniques to the neuroimaging domain has been challenging due to the expansive number of potential preprocessing pipelines and the large parameter search space for graph-based dataset construction. In this paper, we introduce NeuroGraph 1 , a collection of graph-based neuroimaging datasets, and demonstrated its utility for predicting multiple categories of behavioral and cognitive traits. We delve deeply into the dataset generation search space by crafting 35 datasets that encompass static and dynamic brain connectivity, running in excess of 15 baseline methods for benchmarking. Additionally, we provide generic frameworks for learning on both static and dynamic graphs. Our extensive experiments lead to several key observations. Notably, using correlation vectors as node features, incorporating larger number of regions of interest, and employing sparser graphs lead to improved performance. To foster further advancements in graph-based data driven neuroimaging analysis, we offer a comprehensive open-source Python package that includes the benchmark datasets, baseline implementations, model training, and standard evaluation.  \n1[https://anwar-said.github.io/anwarsaid/neurograph.html](https://anwar-said.github.io/anwarsaid/neurograph.html)  \n37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks.  \nTable 1: Dataset statistics. |G| denotes the number of graphs, |N|avg and |E|avg denote the average number of nodes and edges, d indicates the degree, and K signifies the global clustering coefficient.  \n\n| Dataset |  | Statistics |  |  |  |  |  | Node Feat.\u003Cbr>(dim) | \\#Classes | Prediction Task |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  |  | |G| | |N| avg | |E| avg | dmax | davg | Kavg |  |  |  |\n| Static | HCP-Task | 7443 | 400 | 7029.18 | 153 | 17.572 | 0.410 | 400 | 7 | Graph Classification |\n|  | HCP-Gender | 1078 | 1000 | 45578.61 | 413 | 45.579 | 0.466 | 1000 | 2 | Graph Classification |\n|  | HCP-Age | 1065 | 1000 | 45588.40 | 413 | 45.588 | 0.466 | 1000 | 3 | Graph Classification |\n|  | HCP-FI | 1071 | 1000 | 45573.67 | 413 | 45.574 | 0.466 | 1000 | - | Graph Regression |\n|  | HCP-WM | 1078 | 1000 | 45578.61 | 413 | 45.579 | 0.466 | 1000 | - | Graph Regression |\n\n\n| Dynamic | DynHCP-Task | 7443 | 100 | 843.04 | 57 | 8.430 | 0.427 | 100 | 7 | Graph Classification |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  | DynHCP-Gender | 1080 | 100 | 874.88 | 53 | 8.749 | 0.439 | 100 | 2 | Graph Classificat","cbCaiovi8t0JqMXz","https://ap.wps.com/l/cbCaiovi8t0JqMXz","pdf",2425503,1,22,"English","en",105,"# Abstract\n# Introduction\n## Objectives and challenges\n## Dataset generation and benchmarking\n# Dataset statistics","[{\"question\":\"What problem does NeuroGraph address in graph-based neuroimaging research?\",\"answer\":\"It addresses the difficulty of applying graph machine learning to neuroimaging due to many possible fMRI preprocessing pipelines, the lack of an intuitive way to generate graph representations, and knowledge gaps between neuroimaging and graph ML.\"},{\"question\":\"What does the NeuroGraph benchmark include?\",\"answer\":\"It introduces graph-based neuroimaging datasets and creates 35 datasets spanning static and dynamic brain connectivity, evaluated with 15+ baseline methods for benchmarking.\"},{\"question\":\"What open-source resources are provided to support further work?\",\"answer\":\"An open-source Python package is provided, including benchmark datasets, baseline implementations, model training workflows, and standard evaluation tools.\"}]","NeuroGraph - Benchmarks for Graph Machine Learning in Brain Connectomics | PDF",1785727050,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"neurograph-benchmarks-for-graph-machine-learning-in-brain-connectomics","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/neurograph-benchmarks-for-graph-machine-learning-in-brain-connectomics/119929/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does NeuroGraph address in graph-based neuroimaging research?","Question",{"text":75,"@type":76},"It addresses the difficulty of applying graph machine learning to neuroimaging due to many possible fMRI preprocessing pipelines, the lack of an intuitive way to generate graph representations, and knowledge gaps between neuroimaging and graph ML.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the NeuroGraph benchmark include?",{"text":80,"@type":76},"It introduces graph-based neuroimaging datasets and creates 35 datasets spanning static and dynamic brain connectivity, evaluated with 15+ baseline methods for benchmarking.",{"name":82,"@type":73,"acceptedAnswer":83},"What open-source resources are provided to support further work?",{"text":84,"@type":76},"An open-source Python package is provided, including benchmark datasets, baseline implementations, model training workflows, and standard evaluation tools.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]