| Presentation | 2021-03-02 Learning from Noisy Complementary Labels with Robust Loss Functions Hiroki Ishiguro, Takashi Ishida, Masashi Sugiyama, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | It has been demonstrated that large-scale labeled datasets facilitate the success of machine learning. However, collecting labeled data is often very costly and error-prone in practice. To cope with this problem, previous studies have considered the use of a complementary label, which specifies a class that an instance does not belong to and can be collected more easily than ordinary labels. However, complementary labels could also be error-prone and thus mitigating the influence of label noise is an important challenge to make complementary-label learning more useful in practice. In this paper, we derive conditions for the loss function such that the learning algorithm is not affected by noise in complementary labels. Experiments on benchmark datasets with noisy complementary labels demonstrate that the loss functions that satisfy our conditions significantly improve the classification performance. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | complementary label / label noise / robust loss function / loss correction |
| Paper # | IBISML2020-34 |
| Date of Issue | 2021-02-23 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2021/3/2(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Organized and general sessions on machine learning |
| Chair | Ichiro Takeuchi(Nagoya Inst. of Tech.) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Masashi Sugiyama(AIST) / Koji Tsuda(NTT) |
| Assistant | Atsuyoshi Nakamura(Hokkaido Univ.) / Shigeyuki Oba(Miidas) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Learning from Noisy Complementary Labels with Robust Loss Functions |
| Sub Title (in English) | |
| Keyword(1) | complementary label |
| Keyword(2) | label noise |
| Keyword(3) | robust loss function |
| Keyword(4) | loss correction |
| 1st Author's Name | Hiroki Ishiguro |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Takashi Ishida |
| 2nd Author's Affiliation | The University of Tokyo/RIKEN(UTokyo/RIKEN) |
| 3rd Author's Name | Masashi Sugiyama |
| 3rd Author's Affiliation | RIKEN/The University of Tokyo(RIKEN/UTokyo) |
| Date | 2021-03-02 |
| Paper # | IBISML2020-34 |
| Volume (vol) | vol.120 |
| Number (no) | IBISML-395 |
| Page | pp.pp.1-8(IBISML), |
| #Pages | 8 |
| Date of Issue | 2021-02-23 (IBISML) |