Diffusion-Augmented Neural Processes

Lorenzo Bonito, James Requeima, Aliaksandra Shysheya, Richard E. Turner

11/16/2023

cs.LG

No confident code implementation found for this paper.

Abstract

Over the last few years, Neural Processes have become a useful modelling tool in many application areas, such as healthcare and climate sciences, in which data are scarce and prediction uncertainty estimates are indispensable. However, the current state of the art in the field (AR CNPs; Bruinsma et al., 2023) presents a few issues that prevent its widespread deployment. This work proposes an alternative, diffusion-based approach to NPs which, through conditioning on noised datasets, addresses many of these limitations, whilst also exceeding SOTA performance.

View on arXiv View PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Neural Network Diffusion

84% match1 repo8862024

Neural Bridge Processes

83% match2025

Neural Diffusion Models

83% match2026

Neural Diffusion Intensity Models for Point Process Data

83% match2026

A Comprehensive Survey on Knowledge Distillation of Diffusion Models

83% match2023

Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling

82% match2024

Cite this paper

@article{bonito2023diffusionaugmented,
  title  = {Diffusion-Augmented Neural Processes},
  author = {Lorenzo Bonito and James Requeima and Aliaksandra Shysheya and Richard E. Turner},
  year   = {2023},
  eprint = {2311.09848},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.09848v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/2311.09848.svg)](https://codeofpaper.com/paper/2311.09848)