用微分熵提升自编码器在分布外样本下的投影可靠性
DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy
- 引入微分熵建模嵌入空间不确定性，增强投影鲁棒性
- 在4个数据集上实现与现有方法相当的投影精度
- 适合需要评估降维结果可信度的研究者使用
近期，自编码器（AEs）被用于构建多维数据的参数化和可逆投影。参数化投影可对新样本直接嵌入而无需重新计算整体投影，可逆投影则支持生成新数据实例。然而，现有方法在数据或嵌入空间的分布外样本上表现不佳。为此，我们提出DE-VAE，一种基于微分熵（DE）的不确定性感知变分自编码器，以改进学习到的参数化和可逆投影。给定固定投影，训练DE-VAE学习从高维到2D空间的映射及反向映射。我们在四个知名数据集上进行定量与定性评估，以UMAP和t-SNE为基线方法。结果表明，DE-VAE在保持与其他当前基于AE方法相当投影准确率的同时，能够分析嵌入不确定性。
原文摘要 · Abstract (English)
Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection, while invertible projections allow the synthesis of new data instances. However, existing methods perform poorly when dealing with out-of-distribution samples in either the data or embedding space. Thus, we propose DE-VAE, an uncertainty-aware variational AE using differential entropy (DE) to improve the learned parametric and invertible projections. Given a fixed projection, we train DE-VAE to learn a mapping into 2D space and an inverse mapping back to the original space. We conduct quantitative and qualitative evaluations on four well-known datasets, using UMAP and t-SNE as baseline projection methods. Our findings show that DE-VAE can create parametric and inverse projections with comparable accuracy to other current AE-based approaches while enabling the analysis of embedding uncertainty.
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。