提出可满足多种条件的表格数据生成方法，突破现有方法泛化能力差的瓶颈。
Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
- 基于流形理论设计推理时通用的引导机制
- 在多个数据集上实现精准条件生成与不等式约束满足
- 适合需要精细控制生成过程的表格数据应用
在生成过程中精确控制条件对实际应用至关重要。现有方法依赖训练阶段策略，无法泛化到推理阶段未见约束，且难以处理表格式插补之外的条件任务。尽管流形理论为生成提供理论指导，但当前方法仅适用于特定推理目标，且局限于连续领域。本文将流形理论拓展至表格数据，并扩展其适用范围以支持多样化的推理目标。在此基础上，提出HARPOON——一种表格扩散模型，通过沿流形几何引导无约束样本，在推理阶段满足多种表格条件。我们在插补和不等式约束等任务上验证了理论贡献，结果表明HARPOON在多个数据集上表现优异，证明了流形感知引导在表格数据生成中的实际价值。
原文摘要 · Abstract (English)
Generating tabular data under conditions is critical to applications requiring precise control over the generative process. Existing methods rely on training-time strategies that do not generalise to unseen constraints during inference, and struggle to handle conditional tasks beyond tabular imputation. While manifold theory offers a principled way to guide generation, current formulations are tied to specific inference-time objectives and are limited to continuous domains. We extend manifold theory to tabular data and expand its scope to handle diverse inference-time objectives. On this foundation, we introduce HARPOON, a tabular diffusion method that guides unconstrained samples along the manifold geometry to satisfy diverse tabular conditions at inference. We validate our theoretical contributions empirically on tasks such as imputation and enforcing inequality constraints, demonstrating HARPOON'S strong performance across diverse datasets and the practical benefits of manifold-aware guidance for tabular data. Code URL: https://github.com/adis98/Harpoon
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。