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 demonstrate that the proposed dPoE outperforms baselines markedly.

翻译：多视角甚至多模态数据在实际应用中极具吸引力但充满挑战。多视角数据中的异常检测是近期突出的研究课题。然而，现有方法大多存在以下问题：1）仅适用于两视角或特定类型的异常；2）面临融合解耦难题；3）不支持模型部署后的在线检测。为应对这些挑战，本文的核心思想包含三方面：多视角学习、解耦表征学习与生成模型。为此，我们提出dPoE——一种新型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（Product-of-Experts, PoE）层；（2）用于解耦视角公共表征与视角特有表征的全修正（Total Correction, TC）判别器；（3）整合所有组件的联合损失函数。此外，我们推导了控制视角公共表征与视角特有表征的理论信息界。在六个真实世界数据集上的大量实验表明，所提dPoE模型显著优于基准方法。