arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.13622cs.LG
收藏

流形解码器:从非线性嵌入进行生成建模的框架

Manifold Decoders: A Framework for Generative Modeling from Nonlinear Embeddings

Department of Computer & Information Science & Engineering, University of Florida(计算机与信息科学与工程系,佛罗里达大学)

Riddhish Thakare, Kingdom Mutala Akugri

AI总结:

本文提出流形解码器框架,为经典非线性降维方法构建神经解码器以实现双向映射,并集成扩散生成过程;实验表明其重建质量不及自编码器,流形约束扩散样本质量差,揭示NLDR方法在生成建模中的固有局限。

摘要:

经典的非线性降维(NLDR)技术,如t-SNE、Isomap和LLE,在创建用于数据可视化的低维嵌入方面表现出色,但根本上缺乏将这些嵌入映射回原始高维空间的能力。这种单向变换限制了它们在生成应用中的使用。本文通过引入一个系统性的框架来构建针对著名NLDR方法的神经解码器架构,首次实现了双向映射,从而解决了这一关键空白。我们通过实现一个基于扩散的生成过程来扩展该框架,该过程直接在这些学习到的流形空间内运行。通过在CelebA数据集上的实验,我们评估了我们的方法相对于自编码器和标准扩散模型基线在重建和生成性能方面的表现。我们的发现揭示了一个基本的权衡:虽然解码器成功重建了数据,但其质量被端到端优化的自编码器所超越。此外,流形约束的扩散产生了质量较差的样本,这表明经典NLDR嵌入的离散和稀疏特性不适合生成模型所需的连续插值。这项工作突显了将生成能力改造到主要为可视化和分析而设计的NLDR方法上时固有的挑战。

英文摘要:

Classical nonlinear dimensionality reduction (NLDR) techniques like t-SNE, Isomap, and LLE excel at creating low-dimensional embeddings for data visualization but fundamentally lack the ability to map these embeddings back to the original high-dimensional space. This one-way transformation limits their use in generative applications. This paper addresses this critical gap by introducing a system- atic framework for constructing neural decoder architectures for prominent NLDR methods, enabling bidirectional mapping for the first time. We extend this framework by implementing a diffusion-based generative process that operates directly within these learned manifold spaces. Through experiments on the CelebA dataset, we evaluate the reconstruction and generative performance of our approach against autoencoder and standard diffusion model baselines. Our findings reveal a fundamental trade- off: while the decoders successfully reconstruct data, their quality is surpassed by end-to-end optimized autoencoders. Moreover, manifold-constrained diffusion yields poor-quality samples, suggesting that the discrete and sparse nature of classical NLDR embeddings is ill-suited for the continuous inter- polation required by generative models. This work highlights the inherent challenges in retrofitting generative capabilities onto NLDR methods designed primarily for visualization and analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑