ComCo: Complementary supervised contrastive learning for complementary label learning
文献类型：期刊论文
| 作者 | Jiang, Haoran2,3,7; Sun, Zhihao5,6; Tian, Yingjie1,2,3,4 |
| 刊名 | NEURAL NETWORKS
 |
| 出版日期 | 2024 |
| 卷号 | 169页码:44-56 |
| 关键词 | Complementary label learning Weakly supervised learning Contrastive learning Machine learning Representation learning |
| ISSN号 | 0893-6080 |
| DOI | 10.1016/j.neunet.2023.10.013 |
| 英文摘要 | Complementary label learning (CLL) is an important problem that aims to reduce the cost of obtaining largescale accurate datasets by only allowing each training sample to be equipped with labels the sample does not belong. Despite its promise, CLL remains a challenging task. Previous methods have proposed new loss functions or introduced deep learning-based models to CLL, but they mostly overlook the semantic information that may be implicit in the complementary labels. In this work, we propose a novel method, ComCo, which leverages a contrastive learning framework to assist CLL. Our method includes two key strategies: a positive selection strategy that identifies reliable positive samples and a negative selection strategy that skillfully integrates and leverages the information in the complementary labels to construct a negative set. These strategies bring ComCo closer to supervised contrastive learning. Empirically, ComCo significantly achieves better representation learning and outperforms the baseline models and the current state-of-the-art by up to 14.61% in CLL. |
| 资助项目 | National Natural Science Foundation of China[12071458,71731009] |
| WOS研究方向 | Computer Science ; Neurosciences & Neurology |
| 语种 | 英语 |
| WOS记录号 | WOS:001103885400001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/38061]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Tian, Yingjie |
| 作者单位 | 1.UCAS, MOE Social Sci Lab Digital Econ Forecasts & Policy, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Res Ctr Fictitious Econ & Data Sci, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Econ & Management, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 6.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 7.Univ Chinese Acad Sci, Sch Math & Sci, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Jiang, Haoran,Sun, Zhihao,Tian, Yingjie. ComCo: Complementary supervised contrastive learning for complementary label learning[J]. NEURAL NETWORKS,2024,169:44-56. |
| APA | Jiang, Haoran,Sun, Zhihao,&Tian, Yingjie.(2024).ComCo: Complementary supervised contrastive learning for complementary label learning.NEURAL NETWORKS,169,44-56. |
| MLA | Jiang, Haoran,et al."ComCo: Complementary supervised contrastive learning for complementary label learning".NEURAL NETWORKS 169(2024):44-56. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。