DnNP: Denoising Input Uncertainty in Neural Processes
Organizations: Electrical & Computer Engineering, Northeastern University, Boston, MA, USA · Civil & Environmental Engineering, Northeastern University, Boston, MA, USA · Marine & Environmental Sciences, Northeastern University, Boston, MA, USA
Abstract
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.
Figures & tables
| Method | NLL | RMSE | Acc |
|---|---|---|---|
| NP | -0.0631 | 0.1413 | 0.706 |
| CNP | -0.00571 | 0.232 | 0.319 |
| ANP | -0.00702 | 0.190 | 0.733 |
| ConvCNP | -0.00454 | 0.213 | 0.576 |
| Dataset | Feature Set | Mean | NP | DnNP (ours) | ||
|---|---|---|---|---|---|---|
| RMSE | NLL | RMSE | NLL | RMSE | ||
| PM2.5 (Air Quality) | Lat, Lon, RH | 0.776 | ||||
| Lat, Lon, Temp | 0.776 | |||||
| Lat, Lon, RH, Temp | 0.776 | |||||
| Pressure (NOAA CA 2026) | Lat, Lon, Temp | 0.108 | ||||
| Lat, Lon, RH | 0.108 | |||||
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
| Dataset | Task | Noise | ||
|---|---|---|---|---|
| 1D GP | 10,000 | 1 | Regression | No |
| MNIST | 70,000 | 2 | Image Compl. | No |
| Air Quality | 2,856 | 4 | Spatial Interp. | Yes |
| NOAA CA 2026 | 90 | 4 | Spatial Interp. | Yes |