{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:44:19Z","timestamp":1723016659344},"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>This paper studies multiparty learning, aiming to learn a model using the private data of different participants. Model reuse is a promising solution for multiparty learning, assuming that a local model has been trained for each party. Considering the potential sample selection bias among different parties, some heterogeneous model reuse approaches have been developed. However, although pre-trained local classifiers are utilized in these approaches, the characteristics of the local data are not well exploited. This motivates us to estimate the density of local data and design an auxiliary model together with the local classifiers for reuse. To address the scenarios where some local models are not well pre-trained, we further design a multiparty cross-entropy loss for calibration. Upon existing works, we address a challenging problem of heterogeneous model reuse from a decision theory perspective and take advantage of recent advances in density estimation. Experimental results on both synthetic and benchmark data demonstrate the superiority of the proposed method.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/472","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:31:30Z","timestamp":1691742690000},"page":"4244-4252","source":"Crossref","is-referenced-by-count":0,"title":["Improving Heterogeneous Model Reuse by Density Estimation"],"prefix":"10.24963","author":[{"given":"Anke","family":"Tang","sequence":"first","affiliation":[{"name":"Wuhan University, China"},{"name":"Hubei Luojia Laboratory, Wuhan, China"}]},{"given":"Yong","family":"Luo","sequence":"additional","affiliation":[{"name":"Wuhan University, China"},{"name":"Hubei Luojia Laboratory, Wuhan, China"}]},{"given":"Han","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, China"}]},{"given":"Fengxiang","family":"He","sequence":"additional","affiliation":[{"name":"JD Explore Academy, JD.com, Inc., China"}]},{"given":"Kehua","family":"Su","sequence":"additional","affiliation":[{"name":"Wuhan University, China"}]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"Wuhan University, China"},{"name":"Hubei Luojia Laboratory, Wuhan, China"}]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis, USA"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Australia"}]}],"member":"10584","event":{"number":"32","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2023","name":"Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}","start":{"date-parts":[[2023,8,19]]},"theme":"Artificial Intelligence","location":"Macau, SAR China","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":"2023-08-11T08:49:21Z","timestamp":1691743761000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/472"}},"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\/472","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}