{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:02:22Z","timestamp":1774454542001,"version":"3.50.1"},"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":[[2023,8]]},"abstract":"<jats:p>Confidence calibration - the process to calibrate the output probability distribution of neural networks - is essential for safety-critical applications of such networks. Recent works verify the link between mis-calibration and overfitting. However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks. In this work, we study the limitions of early stopping and comprehensively analyze the overfitting problem of a network considering each individual block. We then propose a novel regularization method, predecessor combination search (PCS), to improve calibration by searching a combination of best-fitting block predecessors, where block predecessors are the corresponding network blocks with weight parameters from earlier training stages. PCS achieves the state-of-the-art calibration performance on multiple datasets and architectures. In addition, PCS improves model robustness under dataset distribution shift. Supplementary material and code are available at https:\/\/github.com\/Linwei94\/PCS<\/jats:p>","DOI":"10.24963\/ijcai.2023\/475","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:31:30Z","timestamp":1691742690000},"page":"4271-4279","source":"Crossref","is-referenced-by-count":4,"title":["Calibrating a Deep Neural Network with Its Predecessors"],"prefix":"10.24963","author":[{"given":"Linwei","family":"Tao","sequence":"first","affiliation":[{"name":"University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjing","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daochang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changming","family":"Sun","sequence":"additional","affiliation":[{"name":"CSIRO Data61"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}","theme":"Artificial Intelligence","location":"Macau, SAR China","acronym":"IJCAI-2023","number":"32","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2023,8,19]]},"end":{"date-parts":[[2023,8,25]]}},"container-title":["Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:49:24Z","timestamp":1691743764000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/475"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2023\/475","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}