Automated Graph Machine Learning: Approaches, Libraries and Directions. Wang, X., Zhang, Z., & Zhu, W. arXiv:2201.01288 [cs], January, 2022. arXiv: 2201.01288Paper abstract bibtex 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 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. 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.
@article{wang_automated_2022,
title = {Automated {Graph} {Machine} {Learning}: {Approaches}, {Libraries} and {Directions}},
shorttitle = {Automated {Graph} {Machine} {Learning}},
url = {http://arxiv.org/abs/2201.01288},
abstract = {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 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. 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.},
language = {en},
urldate = {2022-01-19},
journal = {arXiv:2201.01288 [cs]},
author = {Wang, Xin and Zhang, Ziwei and Zhu, Wenwu},
month = jan,
year = {2022},
note = {arXiv: 2201.01288},
keywords = {/unread, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, ⛔ No DOI found},
}
Downloads: 0
{"_id":"egjbMATSfiTQ3natM","bibbaseid":"wang-zhang-zhu-automatedgraphmachinelearningapproacheslibrariesanddirections-2022","author_short":["Wang, X.","Zhang, Z.","Zhu, W."],"bibdata":{"bibtype":"article","type":"article","title":"Automated Graph Machine Learning: Approaches, Libraries and Directions","shorttitle":"Automated Graph Machine Learning","url":"http://arxiv.org/abs/2201.01288","abstract":"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 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. 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.","language":"en","urldate":"2022-01-19","journal":"arXiv:2201.01288 [cs]","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Xin"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Ziwei"],"suffixes":[]},{"propositions":[],"lastnames":["Zhu"],"firstnames":["Wenwu"],"suffixes":[]}],"month":"January","year":"2022","note":"arXiv: 2201.01288","keywords":"/unread, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, ⛔ No DOI found","bibtex":"@article{wang_automated_2022,\n\ttitle = {Automated {Graph} {Machine} {Learning}: {Approaches}, {Libraries} and {Directions}},\n\tshorttitle = {Automated {Graph} {Machine} {Learning}},\n\turl = {http://arxiv.org/abs/2201.01288},\n\tabstract = {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 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. 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.},\n\tlanguage = {en},\n\turldate = {2022-01-19},\n\tjournal = {arXiv:2201.01288 [cs]},\n\tauthor = {Wang, Xin and Zhang, Ziwei and Zhu, Wenwu},\n\tmonth = jan,\n\tyear = {2022},\n\tnote = {arXiv: 2201.01288},\n\tkeywords = {/unread, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, ⛔ No DOI found},\n}\n\n","author_short":["Wang, X.","Zhang, Z.","Zhu, W."],"key":"wang_automated_2022","id":"wang_automated_2022","bibbaseid":"wang-zhang-zhu-automatedgraphmachinelearningapproacheslibrariesanddirections-2022","role":"author","urls":{"Paper":"http://arxiv.org/abs/2201.01288"},"keyword":["/unread","Computer Science - Artificial Intelligence","Computer Science - Machine Learning","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread","computer science - artificial intelligence","computer science - machine learning","⛔ no doi found"],"search_terms":["automated","graph","machine","learning","approaches","libraries","directions","wang","zhang","zhu"],"title":"Automated Graph Machine Learning: Approaches, Libraries and Directions","year":2022}