{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:43:05Z","timestamp":1723016585839},"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>Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous generalization bound. The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound. However, it requires the computation of expensive second-order curvature, which hinders its practical application. In this paper, we establish the connection between the recognizability of representations and the recent functional conditional mutual information (f-CMI) generalization bound, which is significantly easier to estimate. On this basis we propose a Recognizable Information Bottleneck (RIB) which regularizes the recognizability of representations through a recognizability critic optimized by density ratio matching under the Bregman divergence. Extensive experiments on several commonly used datasets demonstrate the effectiveness of the proposed method in regularizing the model and estimating the generalization gap.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/448","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T04:31:30Z","timestamp":1691728290000},"page":"4028-4036","source":"Crossref","is-referenced-by-count":0,"title":["Recognizable Information Bottleneck"],"prefix":"10.24963","author":[{"given":"Yilin","family":"Lyu","sequence":"first","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University"}]},{"given":"Mingyang","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University"}]},{"given":"Xinyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University"}]},{"given":"Yaxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Mathematics, School of Science, Shanghai University"}]},{"given":"Tieyong","family":"Zeng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Liping","family":"Jing","sequence":"additional","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University"}]}],"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":"2023-08-11T04:48:45Z","timestamp":1691729325000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/448"}},"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\/448","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}