{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:41:31Z","timestamp":1723016491956},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>We argue that the present setting of semisupervised learning on graphs may result in unfair comparisons, due to its potential risk of over-tuning hyper-parameters for models. In this paper, we highlight the significant influence of tuning hyper-parameters, which leverages the label information in the validation set to improve the performance. To explore the limit of over-tuning hyperparameters, we propose ValidUtil, an approach to fully utilize the label information in the validation set through an extra group of hyper-parameters. With ValidUtil, even GCN can easily get high accuracy of 85.8% on Cora.\n\nTo avoid over-tuning, we merge the training set and the validation set and construct an i.i.d. graph benchmark (IGB) consisting of 4 datasets. Each dataset contains 100 i.i.d. graphs sampled from a large graph to reduce the evaluation variance. Our experiments suggest that IGB is a more stable benchmark than previous datasets for semisupervised learning on graphs. Our code and data are released at https:\/\/github.com\/THUDM\/IGB\/.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/450","type":"proceedings-article","created":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T22:55:56Z","timestamp":1657925756000},"page":"3243-3249","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking the Setting of Semi-supervised Learning on Graphs"],"prefix":"10.24963","author":[{"given":"Ziang","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University"}]},{"given":"Ming","family":"Ding","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Weikai","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Ziyu","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yukuo","family":"Cen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Jie","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T07:09:47Z","timestamp":1658128187000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/450"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/450","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}