提出结构外推数据生成框架，让模型生成训练数据之外的新内容。
SEDGE: Structural Extrapolated Data Generation
- 基于数据生成过程的假设，设计结构感知的优化与扩散采样方法。
- 在保守假设下可近似识别新数据分布，否则无法唯一确定分布。
- 在合成数据和图像生成中验证了生成效果，适用于需要突破训练范围的场景。
本文针对训练数据之外的数据生成难题，提出基于数据生成过程合理假设的结构外推数据生成框架（SEDGE）。我们给出了在何种条件下可可靠生成符合新规格的数据，并在某些“保守”假设下实现了此类数据分布的近似可识别性，而无这些假设时则存在固有的不可识别性。算法层面，提出了基于结构信息优化策略或扩散后验采样的实用生成方法。通过合成数据实验以及真实场景下的图像外推生成，验证了该框架的有效性。
原文摘要 · Abstract (English)
This paper aims to address the challenge of data generation beyond the training data and proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable assumptions on the underlying data-generating process. We provide conditions under which data satisfying novel specifications can be generated reliably, together with the approximate identifiability of the distribution of such data under certain ``conservative" assumptions, as well as the inherent non-identifiability of this distribution without such assumptions. On the algorithmic side, we develop practical methods to achieve extrapolated data generation, based on a structure-informed optimization strategy or diffusion posterior sampling, respectively. We verify the extrapolation performance on synthetic data and also consider extrapolated image generation as a real-world scenario to illustrate the validity of the proposed framework.
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。