通过自动化训练停止释放无监督深度异常检测的潜力
Unleashing the Potential of Unsupervised Deep Outlier Detection through Automated Training Stopping
AI总结：
针对深度异常检测模型对训练时间等超参数高度敏感且无标签难以选优的问题，提出损失熵指标与自动化训练停止算法，无需标签即可在最优迭代终止训练，提升模型鲁棒性与性能并显著减少训练时间。
摘要：
异常检测（OD）因其广泛的应用而持续受到研究关注。随着深度学习的发展，越来越多的深度异常检测算法被提出。尽管已有大量深度异常检测模型，现有研究指出，深度模型的性能对超参数（HPs）的配置极其敏感。然而，由于缺乏任何标签且超参数众多，深度异常检测模型的超参数选择仍然是一项极其困难的任务。在我们的研究中，我们揭示了一个关键因素——训练时间，它会给深度模型的性能带来显著波动。即使性能在其他超参数上保持稳定，训练时间本身也可能引发严重的超参数敏感性问题。受这一发现的启发，我们致力于制定一种在最优迭代处终止模型训练的策略。具体而言，我们提出了一种名为损失熵（loss entropy）的新指标，用于在训练过程中内部评估模型性能，同时设计了一种自动化训练停止算法。据我们所知，我们的方法是首个能够在训练过程中无需任何标签即可可靠识别最优训练迭代的方法。我们在表格数据和图像数据集上的实验表明，我们的方法可应用于多种深度模型和数据集。与朴素训练相比，它不仅增强了深度模型对其超参数的鲁棒性，还提升了性能并大幅减少了训练时间。
英文摘要：
Outlier detection (OD) has received continuous research interests due to its wide applications. With the development of deep learning, increasingly deep OD algorithms are proposed. Despite the availability of numerous deep OD models, existing research has reported that the performance of deep models is extremely sensitive to the configuration of hyperparameters (HPs). However, the selection of HPs for deep OD models remains a notoriously difficult task due to the lack of any labels and long list of HPs. In our study. we shed light on an essential factor, training time, that can introduce significant variation in the performance of deep model. Even the performance is stable across other HPs, training time itself can cause a serious HP sensitivity issue. Motivated by this finding, we are dedicated to formulating a strategy to terminate model training at the optimal iteration. Specifically, we propose a novel metric called loss entropy to internally evaluate the model performance during training while an automated training stopping algorithm is devised. To our knowledge, our approach is the first to enable reliable identification of the optimal training iteration during training without requiring any labels. Our experiments on tabular, image datasets show that our approach can be applied to diverse deep models and datasets. It not only enhances the robustness of deep models to their HPs, but also improves the performance and reduces plenty of training time compared to naive training.
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。
