通过关联潜在空间提升多视角数据缺失值填补效果
Correlating Variational Autoencoders Natively For Multi-View Imputation
- 设计联合先验，显式建模多个变分自编码器间的潜在变量相关性
- 在真实数据上实现比传统方法更高精度的缺失视角重建
- 适合处理生物医学等多源异构数据的缺失值补全任务
同一来源的多视角数据通常存在相关性，这种相关性反映在分别训练于各视角数据的变分自编码器（VAE）的潜在空间之间。本文提出一种多视角VAE方法，引入具有非零相关结构的联合先验，以强制潜在空间间存在相关性，从而揭示更紧密相关的潜在表示。利用条件分布可在不同潜在空间间转换，实现缺失视角的重构并用于下游分析。学习该相关结构需保持先验分布的有效性，以及支持端到端训练的参数化方式。
原文摘要 · Abstract (English)
Multi-view data from the same source often exhibit correlation. This is mirrored in correlation between the latent spaces of separate variational autoencoders (VAEs) trained on each data-view. A multi-view VAE approach is proposed that incorporates a joint prior with a non-zero correlation structure between the latent spaces of the VAEs. By enforcing such correlation structure, more strongly correlated latent spaces are uncovered. Using conditional distributions to move between these latent spaces, missing views can be imputed and used for downstream analysis. Learning this correlation structure involves maintaining validity of the prior distribution, as well as a successful parameterization that allows end-to-end learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。