arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.07557cs.LGcs.AI
收藏

面向异常检测的终身持续学习:新挑战、视角与见解

Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights

AGH University of Krakow(克拉科夫AGH科技大学);American University(美利坚大学)

Kamil Faber, Roberto Corizzo, Bartlomiej Sniezynski, Nathalie Japkowicz

AI总结:

本文探讨终身异常检测的基础问题,定义其挑战与学习场景生成方法,并通过实验揭示现有异常检测方法在终身学习设置下的性能差距,论证其对构建鲁棒模型的重要性。

摘要:

异常检测在许多以行为演化为特征的现实领域中至关重要。终身学习代表了一种新兴趋势,满足了机器学习模型在动态环境中持续适应新挑战同时保留过去知识的需求。然而,为终身异常检测构建基础的工作十分有限,与更广泛探索的分类设置相比,终身异常检测带来了本质不同的挑战。在本文中,我们通过探索、激励和讨论终身异常检测来面对这一问题,试图为其更广泛的采用奠定基础。首先,我们解释了终身异常检测为何具有现实意义,定义了设计能够应对终身学习复杂性的异常检测方法所面临的挑战与机遇。其次,我们刻画了学习设置和一种场景生成程序,使研究人员能够利用现有数据集对终身异常检测进行实验。第三,我们在所提出的终身场景上使用流行的异常检测方法进行了实验,强调了采用终身学习可能带来的性能差距。总体而言,我们得出结论:采用终身异常检测对于设计更鲁棒的模型非常重要,这些模型能够提供对环境的全面视图,并同时实现适应与知识保留。

英文摘要:

Anomaly detection is of paramount importance in many real-world domains, characterized by evolving behavior. Lifelong learning represents an emerging trend, answering the need for machine learning models that continuously adapt to new challenges in dynamic environments while retaining past knowledge. However, limited efforts are dedicated to building foundations for lifelong anomaly detection, which provides intrinsically different challenges compared to the more widely explored classification setting. In this paper, we face this issue by exploring, motivating, and discussing lifelong anomaly detection, trying to build foundations for its wider adoption. First, we explain why lifelong anomaly detection is relevant, defining challenges and opportunities to design anomaly detection methods that deal with lifelong learning complexities. Second, we characterize learning settings and a scenario generation procedure that enables researchers to experiment with lifelong anomaly detection using existing datasets. Third, we perform experiments with popular anomaly detection methods on proposed lifelong scenarios, emphasizing the gap in performance that could be gained with the adoption of lifelong learning. Overall, we conclude that the adoption of lifelong anomaly detection is important to design more robust models that provide a comprehensive view of the environment, as well as simultaneous adaptation and knowledge retention.

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。

↑