Multi-view or even multi-modal data is appealing yet challenging for real-world applications. Detecting anomalies in multi-view data is a prominent recent research topic. However, most of the existing methods 1) are only suitable for two views or type-specific anomalies, 2) suffer from the issue of fusion disentanglement, and 3) do not support online detection after model deployment. To address these challenges, our main ideas in this paper are three-fold: multi-view learning, disentangled representation learning, and generative model. To this end, we propose dPoE, a novel multi-view variational autoencoder model that involves (1) a Product-of-Experts (PoE) layer in tackling multi-view data, (2) a Total Correction (TC) discriminator in disentangling view-common and view-specific representations, and (3) a joint loss function in wrapping up all components. In addition, we devise theoretical information bounds to control both view-common and view-specific representations. Extensive experiments on six real-world datasets markedly demonstrate that the proposed dPoE outperforms baselines.

翻译：多视角乃至多模态数据在实际应用中颇具吸引力但充满挑战。检测多视角数据中的异常是近期一个突出的研究课题。然而，现有方法大多存在以下问题：1) 仅适用于双视角或特定类型的异常，2) 受限于融合解耦问题，3) 在模型部署后不支持在线检测。为解决这些挑战，本文的核心思想包含三个方面：多视角学习、解耦表示学习和生成模型。为此，我们提出dPoE——一种新颖的多视角变分自编码器模型，该模型包含：(1) 用于处理多视角数据的专家乘积（PoE）层，(2) 用于解耦视角公共与视角特定表示的全矫正（TC）判别器，(3) 用于整合所有组件的联合损失函数。此外，我们设计了理论信息界来控制视角公共与视角特定表示。在六个真实世界数据集上的大量实验显著表明，所提出的dPoE优于各类基线方法。