{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T22:47:14Z","timestamp":1777589234058,"version":"3.51.4"},"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>We propose a framework for learning calibrated uncertainties under domain shifts, considering the case where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts through the use of a differentiable density ratio estimator and train it together with the task network, composing an adjusted softmax predictive form that concerns the domain shift. In particular, the density ratio estimator yields a density ratio that reflects the closeness of a target (test) sample to the source (training) distribution. We employ it to adjust the uncertainty of prediction in the task network. This idea of using the density ratio is based on the distributionally robust learning (DRL) framework, which accounts for the domain shift through adversarial risk minimization. We demonstrate that our proposed method generates calibrated uncertainties that benefit many downstream tasks, such as unsupervised domain adaptation (UDA) and semi-supervised learning (SSL). On these tasks, methods like self-training and FixMatch use uncertainties to select confident pseudo-labels for re-training. Our experiments show that the introduction of DRL leads to significant improvements in cross-domain performance. We also demonstrate that the estimated density ratios show an agreement with the human selection frequencies, suggesting a positive correlation with a proxy of human perceived uncertainties.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/162","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:31:30Z","timestamp":1691742690000},"page":"1460-1469","source":"Crossref","is-referenced-by-count":2,"title":["Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach"],"prefix":"10.24963","author":[{"given":"Haoxuan","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiding","family":"Yu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yisong","family":"Yue","sequence":"additional","affiliation":[{"name":"California Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Animashree","family":"Anandkumar","sequence":"additional","affiliation":[{"name":"California Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"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":"2023-08-11T08:38:56Z","timestamp":1691743136000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/162"}},"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\/162","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}