High false-positive rate is a long-standing challenge for anomaly detection algorithms, especially in high-stake applications. To identify the true anomalies, in practice, analysts or domain experts will be employed to investigate the top instances one by one in a ranked list of anomalies identified by an anomaly detection system. This verification procedure generates informative labels that can be leveraged to re-rank the anomalies so as to help the analyst to discover more true anomalies given a time budget. Some re-ranking strategies have been proposed to approximate the above sequential decision process. Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback. Then they greedily select the top-1 instance for query. However, these greedy strategies could be sub-optimal since some low-ranked instances could be more helpful in the long-term. In this work, we propose Active Anomaly Detection with Meta-Policy (Meta-AAD), a novel framework that learns a meta-policy for query selection. Specifically, Meta-AAD leverages deep reinforcement learning to train the meta-policy to select the most proper instance to explicitly optimize the number of discovered anomalies throughout the querying process. Meta-AAD is easy to deploy since a trained meta-policy can be directly applied to any new datasets without further tuning. Extensive experiments on 24 benchmark datasets demonstrate that Meta-AAD significantly outperforms the state-of-the-art re-ranking strategies and the unsupervised baseline. The empirical analysis shows that the trained meta-policy is transferable and inherently achieves a balance between long-term and short-term rewards.
Active Anomaly Detection for time-domain discoveries
Université Clermont Auvergne（克莱蒙奥弗涅大学）；CNRS/IN2P3（法国国家科学研究中心/核物理与粒子物理研究所）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；Sternberg Astronomical Institute（斯特恩伯格天文研究所）；National Research University Higher School of Economics（国立研究型大学高等经济学院）；Space Research Institute of the Russian Academy of Sciences (IKI)（俄罗斯科学院空间研究所）；Central Aerohydrodynamic Institute（中央空气流体动力学研究所）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Cinimex（Cinimex公司）
Coniferest: a complete active anomaly detection framework
Lomonosov Moscow State University（莫斯科罗蒙诺索夫国立大学）；Sternberg Astronomical Institute（斯特恩伯格天文研究所）；National Research University Higher School of Economics（国家研究型大学高等经济学院）；McWilliams Center for Cosmology and Astrophysics（麦克威廉姆斯宇宙学与天体物理学中心）；Carnegie Mellon University（卡内基梅隆大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Université Clermont Auvergne（克莱蒙奥弗涅大学）；CNRS/IN2P3（法国国家科学研究中心/核物理与粒子物理研究所）；LPCA（物理化学实验室）
A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection
Dept. of Engineering for Innovation Medicine, University of Verona（创新医学工程系，威尼斯大学）；Faculty of Computer and Information Science, University of Ljubljana（计算机与信息科学系，卢布尔雅那大学）；Qualyco S.r.l.（Qualyco公司）
MLography: An Automated Quantitative Metallography Model for Impurities Anomaly Detection using Novel Data Mining and Deep Learning Approach
Department of Computer Science, Ben-Gurion University of the Negev（内盖夫本古里安大学计算机科学系）；Israel Atomic Energy Commission（以色列原子能委员会）；Department of Physics, Nuclear Research Center-Negev（内盖夫核研究中心物理系）；Department of Materials, Nuclear Research Center-Negev（内盖夫核研究中心材料系）；Ben-Gurion University of the Negev（本古里安大学）；Nuclear Research Center-Negev（内盖夫核研究中心）；Ben-Gurion University of the Negev, Be’er Sheva, Israel（本古里安大学，以色列贝尔谢巴）；Israel Atomic Energy Commission, Tel Aviv, Israel（以色列原子能委员会，特拉维夫，以色列）；Nuclear Research Center-Negev, Be’er-Sheva, Israel（内盖夫核研究中心，贝尔谢巴，以色列）
Dive into Time-Series Anomaly Detection: A Decade Review
Inria（法国国家信息与自动化研究所）；DI ENS（巴黎高等师范学院数字研究所）；PSL（巴黎文理研究大学）；CNRS（法国国家科学研究中心）；The Ohio State University（俄亥俄州立大学）；Université Paris Cité（巴黎西岱大学）；IUF（法国大学研究院）
ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
Department of Electrical and Computer Engineering, McGill University, Canada（麦吉尔大学电气与计算机工程系，加拿大）；Mila - Quebec Artificial Intelligence Institute, Montreal, Canada（魁北克人工智能研究所，蒙特利尔，加拿大）
Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization
Department of Mathematical and Computer Sciences, University of Sarajevo（萨拉热窝大学数学与计算机科学系）；Singidunum University（辛吉杜姆大学）；Trinity University（特里尼蒂大学）；Sinergija University（辛格里雅大学）
