• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
高级检索

面向深度学习的公平性研究综述

陈晋音, 陈奕芃, 陈一鸣, 郑海斌, 纪守领, 时杰, 程瑶

陈晋音, 陈奕芃, 陈一鸣, 郑海斌, 纪守领, 时杰, 程瑶. 面向深度学习的公平性研究综述[J]. 计算机研究与发展, 2021, 58(2): 264-280. DOI: 10.7544/issn1000-1239.2021.20200758
引用本文: 陈晋音, 陈奕芃, 陈一鸣, 郑海斌, 纪守领, 时杰, 程瑶. 面向深度学习的公平性研究综述[J]. 计算机研究与发展, 2021, 58(2): 264-280. DOI: 10.7544/issn1000-1239.2021.20200758
Chen Jinyin, Chen Yipeng, Chen Yiming, Zheng Haibin, Ji Shouling, Shi Jie, Cheng Yao. Fairness Research on Deep Learning[J]. Journal of Computer Research and Development, 2021, 58(2): 264-280. DOI: 10.7544/issn1000-1239.2021.20200758
Citation: Chen Jinyin, Chen Yipeng, Chen Yiming, Zheng Haibin, Ji Shouling, Shi Jie, Cheng Yao. Fairness Research on Deep Learning[J]. Journal of Computer Research and Development, 2021, 58(2): 264-280. DOI: 10.7544/issn1000-1239.2021.20200758
陈晋音, 陈奕芃, 陈一鸣, 郑海斌, 纪守领, 时杰, 程瑶. 面向深度学习的公平性研究综述[J]. 计算机研究与发展, 2021, 58(2): 264-280. CSTR: 32373.14.issn1000-1239.2021.20200758
引用本文: 陈晋音, 陈奕芃, 陈一鸣, 郑海斌, 纪守领, 时杰, 程瑶. 面向深度学习的公平性研究综述[J]. 计算机研究与发展, 2021, 58(2): 264-280. CSTR: 32373.14.issn1000-1239.2021.20200758
Chen Jinyin, Chen Yipeng, Chen Yiming, Zheng Haibin, Ji Shouling, Shi Jie, Cheng Yao. Fairness Research on Deep Learning[J]. Journal of Computer Research and Development, 2021, 58(2): 264-280. CSTR: 32373.14.issn1000-1239.2021.20200758
Citation: Chen Jinyin, Chen Yipeng, Chen Yiming, Zheng Haibin, Ji Shouling, Shi Jie, Cheng Yao. Fairness Research on Deep Learning[J]. Journal of Computer Research and Development, 2021, 58(2): 264-280. CSTR: 32373.14.issn1000-1239.2021.20200758

面向深度学习的公平性研究综述

基金项目: 国家自然科学基金项目(62072406);浙江省自然科学基金项目(LY19F020025);宁波市“科技创新2025”重大专项(2018B10063)
详细信息
  • 中图分类号: TP391

Fairness Research on Deep Learning

Funds: This work was supported by the National Natural Science Foundation of China (62072406), the Natural Science Foundation of Zhejiang Province (LY19F020025), and the Major Special Funding for “Science and Technology Innovation 2025” in Ningbo (2018B10063).
  • 摘要: 深度学习是机器学习研究中的一个重要领域,它具有强大的特征提取能力,且在许多应用中表现出先进的性能,因此在工业界中被广泛应用.然而,由于训练数据标注和模型设计存在偏见,现有的研究表明深度学习在某些应用中可能会强化人类的偏见和歧视,导致决策过程中的不公平现象产生,从而对个人和社会产生潜在的负面影响.为提高深度学习的应用可靠性、推动其在公平领域的发展,针对已有的研究工作,从数据和模型2方面出发,综述了深度学习应用中的偏见来源、针对不同类型偏见的去偏方法、评估去偏效果的公平性评价指标、以及目前主流的去偏平台,最后总结现有公平性研究领域存在的开放问题以及未来的发展趋势.
    Abstract: Deep learning is an important field of machine learning research, which is widely used in industry for its powerful feature extraction capabilities and advanced performance in many applications. However, due to the bias in training data labeling and model design, research shows that deep learning may aggravate human bias and discrimination in some applications, which results in unfairness during the decision-making process, thereby will cause negative impact to both individuals and socials. To improve the reliability of deep learning and promote its development in the field of fairness, we review the sources of bias in deep learning, debiasing methods for different types biases, fairness measure metrics for measuring the effect of debiasing, and current popular debiasing platforms, based on the existing research work. In the end we explore the open issues in existing fairness research field and future development trends.
  • 期刊类型引用(9)

    1. 陈彩华,佘程熙,王庆阳. 可信机器学习综述. 工业工程. 2024(02): 14-26 . 百度学术
    2. 饶高琦,周立炜. 论语言智能的治理. 语言战略研究. 2024(03): 38-48 . 百度学术
    3. 穆春阳,李闯,马行,刘永鹿,杨科,刘宝成. 改进YOLOv7-tiny的轻量化大型铸件焊缝缺陷检测. 组合机床与自动化加工技术. 2024(07): 156-160 . 百度学术
    4. 喻继军,熊明华. 电子商务推荐系统公平性研究进展. 现代信息科技. 2023(14): 115-124 . 百度学术
    5. 范卓娅,孟小峰. 算法公平与公平计算. 计算机研究与发展. 2023(09): 2048-2066 . 本站查看
    6. 吴雷,杜文研,林超然. 基于专利数据应用LDA和N-BEATS组合方法的技术主题预测研究. 数字图书馆论坛. 2023(11): 62-73 . 百度学术
    7. 古天龙,李龙,常亮,罗义琴. 公平机器学习:概念、分析与设计. 计算机学报. 2022(05): 1018-1051 . 百度学术
    8. 王文鑫,张健毅. 联邦学习公平性研究综述. 北京电子科技学院学报. 2022(02): 122-134 . 百度学术
    9. 郁建兴,刘宇轩. 社会治理中的深度学习算法公平性. 信息技术与管理应用. 2022(01): 17-27 . 百度学术

    其他类型引用(13)

计量
  • 文章访问数:  2135
  • HTML全文浏览量:  11
  • PDF下载量:  1294
  • 被引次数: 22
出版历程
  • 发布日期:  2021-01-31

目录

    /

    返回文章
    返回