论文标题
Experts的混合物VAE可能会无视溢流性多模式数据的变化
Mixture-of-experts VAEs can disregard variation in surjective multimodal data
论文作者
论文摘要
机器学习系统通常部署在需要多种模式的数据的领域中，例如表型和基因型特征描述了医疗保健中的患者。以前的工作开发了多模式变异自动编码器（VAE），这些自动编码器（VAE）生成了几种模态。我们考虑主观数据，其中一个模式的单个数据点（例如类标签）描述了来自另一种模态（例如图像）的多个数据点。从理论上讲，我们从理论上和经验上证明，具有专家的混合物的多模式VAE可能难以捕获这种过滤性数据中的可变性。
Machine learning systems are often deployed in domains that entail data from multiple modalities, for example, phenotypic and genotypic characteristics describe patients in healthcare. Previous works have developed multimodal variational autoencoders (VAEs) that generate several modalities. We consider subjective data, where single datapoints from one modality (such as class labels) describe multiple datapoints from another modality (such as images). We theoretically and empirically demonstrate that multimodal VAEs with a mixture of experts posterior can struggle to capture variability in such surjective data.
