Deep Clustering With a Constraint for Topological Invariance Based on Symmetric InfoNCE.
Autor: | Zhang Y; Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8552, Japan zhang.y.av@m.titech.ac.jp., Wada Y; Fujitsu Limited, Nakahara-ku, Kawasaki, Kanagawa 211-8588, Japan.; RIKEN AIP, Chuo-ku, Tokyo 103-0027, Japan wada.yuichiro@jp.fujitsu.com., Waida H; Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8552, Japan waida.h.aa@m.titech.ac.jp., Goto K; Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8552, Japan kaitogoto7@gmail.com., Hino Y; Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8552, Japan blueozk@gmail.com., Kanamori T; Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8552, Japan.; RIKEN AIP, Chuo-ku, Tokyo 103-0027, Japan kanamori@c.titech.ac.jp. |
---|---|
Jazyk: | angličtina |
Zdroj: | Neural computation [Neural Comput] 2023 Jun 12; Vol. 35 (7), pp. 1288-1339. |
DOI: | 10.1162/neco_a_01591 |
Abstrakt: | We consider the scenario of deep clustering, in which the available prior knowledge is limited. In this scenario, few existing state-of-the-art deep clustering methods can perform well for both noncomplex topology and complex topology data sets. To address the problem, we propose a constraint utilizing symmetric InfoNCE, which helps an objective of the deep clustering method in the scenario of training the model so as to be efficient for not only noncomplex topology but also complex topology data sets. Additionally, we provide several theoretical explanations of the reason that the constraint can enhances the performance of deep clustering methods. To confirm the effectiveness of the proposed constraint, we introduce a deep clustering method named MIST, which is a combination of an existing deep clustering method and our constraint. Our numerical experiments via MIST demonstrate that the constraint is effective. In addition, MIST outperforms other state-of-the-art deep clustering methods for most of the commonly used 10 benchmark data sets. (© 2023 Massachusetts Institute of Technology.) |
Databáze: | MEDLINE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |