用邻近点计算加速高斯过程变分自编码器，提升效率与灵活性。
Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
- 仅计算每个数据点的最近邻，降低计算复杂度。
- 在图像补全和生成任务中性能超越现有方法。
- 无需大量诱导点，支持更灵活的核函数选择。
高斯过程变分自编码器（GPVAE）通过将标准变分自编码器中的独立高斯先验替换为高斯过程先验，能够捕捉潜在变量间的丰富相关性。然而，在大规模场景下进行精确的高斯过程推断计算成本过高，导致现有方法通常依赖受限的核假设或大量诱导点。本文提出一种邻近驱动的近似策略，利用潜在空间中的局部邻接关系实现可扩展的GPVAE推断。通过将计算限制在每个数据点的最近邻范围内，该方法保留了关键的潜在依赖结构，支持更灵活的核函数选择，并减少了对大量诱导点的需求。在表示学习、数据补全和条件生成等任务上的大量实验表明，该方法在预测性能和计算效率方面均优于其他GPVAE变体。
原文摘要 · Abstract (English)
Gaussian Process (GP) Variational Autoencoders (VAEs) extend standard VAEs by replacing the fully factorised Gaussian prior with a GP prior, thereby capturing richer correlations among latent variables. However, performing exact GP inference in large-scale GPVAEs is computationally prohibitive, often forcing existing approaches to rely on restrictive kernel assumptions or large sets of inducing points. In this work, we propose a neighbour-driven approximation strategy that exploits local adjacencies in the latent space to achieve scalable GPVAE inference. By confining computations to the nearest neighbours of each data point, our method preserves essential latent dependencies, allowing more flexible kernel choices and mitigating the need for numerous inducing points. Through extensive experiments on tasks including representation learning, data imputation, and conditional generation, we demonstrate that our approach outperforms other GPVAE variants in both predictive performance and computational efficiency.
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。