講演抄録/キーワード |
講演名 |
2017-06-24 10:45
Positive-Unlabeled Learning with Non-Negative Risk Estimator ○Ryuichi Kiryo(Univ. of Tokyo/RIKEN)・Gang Niu(Univ. of Tokyo)・Masashi Sugiyama(RIKEN/Univ. of Tokyo) IBISML2017-4 |
抄録 |
(和) |
From only emph{positive}~(P) and emph{unlabeled}~(U) data, a binary classifier can be trained with PU learning, in which the state of the art is emph{unbiased PU learning}. However, if its model is very flexible, its empirical risk on training data will go negative and we will suffer from serious overfitting. In this paper, we propose a emph{non-negative risk estimator} for PU learning. When being minimized, it is more robust against overfitting and thus we are able to train very flexible models given limited P data. Moreover, we analyze the emph{bias}, emph{consistency} and emph{mean-squared-error reduction} of the proposed risk estimator and the emph{estimation error} of the corresponding risk minimizer. Experiments show that the proposed risk estimator successfully fixes the overfitting problem of its unbiased counterparts. |
(英) |
From only emph{positive}~(P) and emph{unlabeled}~(U) data, a binary classifier can be trained with PU learning, in which the state of the art is emph{unbiased PU learning}. However, if its model is very flexible, its empirical risk on training data will go negative and we will suffer from serious overfitting. In this paper, we propose a emph{non-negative risk estimator} for PU learning. When being minimized, it is more robust against overfitting and thus we are able to train very flexible models given limited P data. Moreover, we analyze the emph{bias}, emph{consistency} and emph{mean-squared-error reduction} of the proposed risk estimator and the emph{estimation error} of the corresponding risk minimizer. Experiments show that the proposed risk estimator successfully fixes the overfitting problem of its unbiased counterparts. |
キーワード |
(和) |
教師付き学習 / 分類問題 / PU学習 / / / / / |
(英) |
Supervised Learning / Classification / Positive-Unlabeled Learning / PU Learning / / / / |
文献情報 |
信学技報, vol. 117, no. 110, IBISML2017-4, pp. 63-70, 2017年6月. |
資料番号 |
IBISML2017-4 |
発行日 |
2017-06-17 (IBISML) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
IBISML2017-4 |
|