DnNP：在 Neural Processes 中显式建模输入噪声的变分去噪方法
DnNP: Denoising Input Uncertainty in Neural Processes
做时空预测或环境传感数据分析的人可以看看这篇。标准 Neural Processes 假设输入干净，DnNP 用变分推理把传感器噪声直接建进模型，PM2.5 插值上 RMSE 降 30%、NLL 降 73%，还给了理论保证，比简单加平滑滤波更有依据。
Neural Processes（NP）框架此前默认输入数据无噪声，而实际场景中传感器噪声和测量误差不可避免，导致预测质量与不确定性估计明显退化。DnNP（Denoising Neural Processes）是 NP 框架的一个原则性扩展，通过变分推理训练，把输入不确定性直接纳入建模，让模型在元学习的同时学习对被污染输入进行去噪。
实验覆盖合成数据与真实数据：在基于真实空气质量传感器的 PM2.5 空间插值任务上，DnNP 相对标准 NP 将 RMSE 最高降低 30%，NLL 最高降低 73%。理论上，作者证明噪声输入下的 Bayes 最优预测器属于 DnNP 模型类，而使用固定观测方差的 plug-in 模型存在不可消除的 KL 散度差距，DnNP 则可以避开这一差距。
DnNP: Denoising Input Uncertainty in Neural Processes
Neural Processes (NPs) are flexible meta-learning models capable of uncertainty quantification across diverse applications. However, the standard NP framework assumes access to noise-free inputs. This is unrealistic in many practical settings, where sensor noise or measurement errors are unavoidable. This discrepancy between model assumptions and real-world data can significantly degrade prediction quality and uncertainty estimates. We introduce Denoising Neural Processes (DnNPs), a principled extension of the NP framework that explicitly models input uncertainty. We train DnNPs via variational inference. DnNPs jointly learn to denoise corrupted inputs and perform meta-learning, making them robust to noisy training data. We demonstrate DnNPs' effectiveness on both synthetic and real-world datasets, showing consistent improvements in prediction and uncertainty quantification compared to standard NPs. On PM2.5 spatial interpolation from real-world air quality sensors, DnNP reduces RMSE by up to 30% and NLL by up to 73% relative to standard NPs. We also provide theoretical grounding: we show that the Bayes-optimal predictor under noisy inputs belongs to the DnNP model class, and that plug-in models with fixed observation variance incur an irreducible KL divergence gap that DnNP provably avoids.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Neural Processes, 变分推理, 不确定性量化, 元学习.
Source attribution: curated from arXiv cs.LG (@Fatemeh Tohidian, Chengzhi Shi, Soomi Lee, Matthew Elia, Amy Mueller, Stratis Ioannidis, Jennifer Dy).