[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117220-en":3,"doc-seo-117220-105":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},117220,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Automated Graph Machine Learning - Approaches, Libraries, Benchmarks and Directions","Graph machine learning is widely studied, yet the rapid growth of graph learning methods makes it increasingly difficult to manually craft optimal algorithms for diverse graph-related tasks and data. The document presents automated graph machine learning as an approach that searches for the best hyper-parameter and neural architecture configurations without manual design. It surveys automated methods including hyper-parameter optimization and neural architecture search, reviews relevant libraries, and introduces AutoGL as an open-source framework. It also proposes a benchmark for unified, reproducible, efficient evaluation and outlines future research directions.","arXiv :2201 .01288v2 [ cs .LG] 2 May 2024  \nAutomated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions  \nXin Wang, Member, IEEE, Ziwei Zhang, Member, IEEE, Haoyang Li, Member, IEEE,  \nand Wenwu Zhu, Fellow, IEEE  \nAbstract—Graph machine learning has been extensively studied in both academic and industry. However, as the literature on graph learning booms with a vast number of emerging methods and techniques, it becomes increasingly difficult to manually design the optimal machine learning algorithm for different graph-related tasks. To tackle the challenge, automated graph machine learning, which aims at discovering the best hyper-parameter and neural architecture configuration for different graph tasks/data without manual design, is gaining an increasing number of attentions from the research community. In this paper, we extensively discuss automated graph machine learning approaches, covering hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning. We briefly overview existing libraries designed for either graph machine learning or automated machine learning respectively, and further in depth introduce AutoGL, our dedicated and the world’s first open-source library for automated graph machine learning. Also, we describe a tailored benchmark that supports unified, reproducible, and efficient evaluations. Last but not least, we share our insights on future research directions for automated graph machine learning. This paper is the first systematic and comprehensive discussion of approaches, libraries as well as directions for automated graph machine learning.  \nIndex Terms—Graph Machine Learning, Graph Neural Network, Automated Machine Learning, AutoML, Neural Architecture Search, Hyper-parameter Optimization  \n~~ ~~ ✦ ~~ ~~  \n1 INTRODUCTION  \nG RAPH data is ubiquitous in our daily life. We can use  \ngraphs to model the complex relationships and dependencies between entities ranging from small molecules in proteins and particles in physical simulations to large national-wide power grids and global airlines. Therefore, graph machine learning, i.e., machine learning on graphs, has long been an important research direction for both academics and industry [1] . In particular, network embedding [2], [3], [4], [5] and graph neural networks (GNNs) [6], [7], [8] have drawn increasing attention in the last decade. They are successfully applied to recommendation systems [9], [10], [11], [12], information retrieval [13],[14], [15], [16], fraud detection [17], bioinformatics [18], [19], physical simulation [20], traffic forecasting [21], [22], knowledge representation [23], drug re-purposing [24], [25] and pandemic prediction [26] for Covid-19 .  \nDespite the popularity of graph machine learning algorithms, the existing literature heavily relies on manual hyper-parameter or architecture design to achieve the best performance, resulting in costly human efforts when a vast number of models emerge for various graph tasks. Take GNNs as an example, at least one hundred new general-purpose architectures have been published in top-tier machine learning and data mining conferences in the year of 2021 alone, not to mention cross-disciplinary researches of  \n• Xin Wang, Ziwei Zhang, Haoyang Li and Wenwu Zhu are with the Department of Computer Science and Technology, Tsinghua University, Beijing, China. Corresponding Authors: Wenwu Zhu. E-mail: {xin wang, zwzhang, [wwzhu](wwzhu}@tsinghua.edu.cn. lihy218@gmail.com)[}](wwzhu}@tsinghua.edu.cn. lihy218@gmail.com)[@tsinghua.edu.cn. lihy218@gmail.com](wwzhu}@tsinghua.edu.cn. lihy218@gmail.com)  \n• This work is supported by the National Key Research and Development Program of China No. 2023YFF1205001, National Natural Science Foundation of China (No. 62222209, 62250008, 62102222) . BNRist under Grant No. BNR2023RC01003, BNR2023TD03006 .  \ntask-specific designs. More and more human efforts are inevitably needed if we stick to the manual try-","cbCaii78l976iCI1","https://ap.wps.com/l/cbCaii78l976iCI1","pdf",1990544,1,20,"English","en",105,"# Introduction\n## Automated Graph Machine Learning Focus\n## Hyper-parameter Optimization and Neural Architecture Search","[{\"question\":\"What problem does automated graph machine learning address?\",\"answer\":\"It targets the difficulty of manually designing optimal algorithms as graph learning methods proliferate. The goal is to obtain strong hyper-parameter and architecture configurations for different graph tasks without manual trial-and-error.\"},{\"question\":\"Which two main topics does the document emphasize?\",\"answer\":\"It focuses on hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning.\"},{\"question\":\"What is AutoGL and how is it positioned?\",\"answer\":\"AutoGL is presented as an open-source library dedicated to automated graph machine learning. The document frames it as the world’s first such open-source library and explains its role in the surveyed ecosystem.\"}]","Automated Graph Machine Learning - Approaches, Libraries, Benchmarks and Directions | PDF",1785674461,50,{"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},"automated-graph-machine-learning-approaches-libraries-benchmarks-and-directions","",{"@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/automated-graph-machine-learning-approaches-libraries-benchmarks-and-directions/117220/",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","2026-08-02",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 automated graph machine learning address?","Question",{"text":75,"@type":76},"It targets the difficulty of manually designing optimal algorithms as graph learning methods proliferate. The goal is to obtain strong hyper-parameter and architecture configurations for different graph tasks without manual trial-and-error.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which two main topics does the document emphasize?",{"text":80,"@type":76},"It focuses on hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What is AutoGL and how is it positioned?",{"text":84,"@type":76},"AutoGL is presented as an open-source library dedicated to automated graph machine learning. The document frames it as the world’s first such open-source library and explains its role in the surveyed ecosystem.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]