arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.06221cs.LG
收藏

开放世界中的分布外数据检测与学习:算法与理论

Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theory

UNIVERSITY OF WISCONSIN–MADISON(威斯康星大学麦迪逊分校)

Yiyou Sun

AI总结:

本论文针对开放世界中的分布外数据检测与表示学习问题,提出了算法解决方案和理论基础,以增强模型对未知类别的识别与学习能力,提升现实应用的可靠性。

摘要:

本论文对机器学习领域做出了重要贡献,特别是在开放世界场景下,系统面临前所未见的数据和情境。传统机器学习模型通常在固定且已知的类别集合内进行训练和测试,这种条件被称为封闭世界设置。虽然这一假设在受控环境中有效,但在现实应用中,当新的数据类别或分类动态且意外地出现时,它就显得不足。为解决这一问题,我们的研究探讨了开放世界机器学习所必需的两个相互关联的步骤:分布外(OOD)检测和开放世界表示学习(ORL)。OOD检测侧重于识别来自未知类别的实例,这些实例超出了模型的训练分布。这一过程降低了对于不熟悉输入做出过于自信、错误预测的风险。超越OOD检测,ORL扩展了模型的能力,不仅能够检测未知实例,还能学习并整合关于这些新类别的知识。通过深入研究开放世界学习的这些研究问题,本论文既贡献了算法解决方案,也提供了理论基础,为构建不仅在性能上出色,而且在面对现实世界不断演变的复杂性时可靠的机器学习模型铺平了道路。

英文摘要:

This thesis makes considerable contributions to the realm of machine learning, specifically in the context of open-world scenarios where systems face previously unseen data and contexts. Traditional machine learning models are usually trained and tested within a fixed and known set of classes, a condition known as the closed-world setting. While this assumption works in controlled environments, it falls short in real-world applications where new classes or categories of data can emerge dynamically and unexpectedly. To address this, our research investigates two intertwined steps essential for open-world machine learning: Out-of-distribution (OOD) Detection and Open-world Representation Learning (ORL). OOD detection focuses on identifying instances from unknown classes that fall outside the model's training distribution. This process reduces the risk of making overly confident, erroneous predictions about unfamiliar inputs. Moving beyond OOD detection, ORL extends the capabilities of the model to not only detect unknown instances but also learn from and incorporate knowledge about these new classes. By delving into these research problems of open-world learning, this thesis contributes both algorithmic solutions and theoretical foundations, which pave the way for building machine learning models that are not only performant but also reliable in the face of the evolving complexities of the real world.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑