Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the many advances in deep learning. In this paper, we consider a critical-yet-understudied challenge with unsupervised DOD, that is, effective hyperparameter (HP) tuning/model selection. While several prior work report the sensitivity of OD models to HPs, it becomes ever so critical for the modern DOD models that exhibit a long list of HPs. We introduce HYPER for tuning DOD models, tackling two fundamental challenges: (1) validation without supervision (due to lack of labeled anomalies), and (2) efficient search of the HP/model space (due to exponential growth in the number of HPs). A key idea is to design and train a novel hypernetwork (HN) that maps HPs onto optimal weights of the main DOD model. In turn, HYPER capitalizes on a single HN that can dynamically generate weights for many DOD models (corresponding to varying HPs), which offers significant speed-up. In addition, it employs meta-learning on historical OD tasks with labels to train a proxy validation function, likewise trained with our proposed HN efficiently. Extensive experiments on 35 OD tasks show that HYPER achieves high performance against 8 baselines with significant efficiency gains.

翻译：离群检测（OD）广泛应用于众多技术文献中。基于深度神经网络的离群检测（DOD）因深度学习领域的诸多进展而近期备受关注。本文探讨了无监督DOD中一个关键但尚未充分研究的挑战，即超参数（HP）调整/模型选择的有效性。尽管先前多项研究指出OD模型对HP敏感，但对于现代DOD模型（其HP列表冗长）而言，这一问题尤为关键。我们提出了HYPER方法用于调整DOD模型，旨在解决两个基本难题：（1）缺乏监督验证（因缺少标记异常），（2）HP/模型空间的高效搜索（因HP数量呈指数增长）。核心思想是设计并训练一种新型超网络（HN），该网络将HP映射至主DOD模型的最优权重。进而，HYPER利用单一超网络动态生成多个DOD模型（对应不同HP）的权重，显著提升速度。此外，该方法在历史带标签的OD任务上采用元学习训练代理验证函数，同样通过我们提出的超网络高效实现。在35个OD任务上的广泛实验表明，HYPER相较8种基线方法实现了高性能且显著提升效率。