无需显式噪声条件，图扩散模型也能高效去噪。
Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models
- 通过伯努利边翻转建模噪声，理论证明可隐式推断噪声水平。
- 无条件模型在真实与合成数据上表现不逊于有条件模型，参数少4-6%，速度提升8-10%。
- 适合追求轻量高效图生成的开发者或研究者使用。
显式噪声级别条件通常被视为图扩散模型（GDMs）有效运行的关键。本文挑战这一假设，探究去噪器能否直接从受损图结构中隐式推断噪声水平，从而避免显式噪声条件。为此，我们构建以伯努利边翻转噪声为核心的理论框架，并拓展至包含结构-属性耦合噪声的复杂场景。在合成及真实世界图数据集上，基于GDSS和DiGress等模型的大量实验验证了理论结论：无条件GDMs性能与有条件模型相当甚至更优，同时参数减少4-6%，计算时间降低8-10%。结果表明，图数据的高维特性本身常蕴含足够去噪信息，为更简洁高效的GDM架构开辟了新路径。
原文摘要 · Abstract (English)
Explicit noise-level conditioning is widely regarded as essential for the effective operation of Graph Diffusion Models (GDMs). In this work, we challenge this assumption by investigating whether denoisers can implicitly infer noise levels directly from corrupted graph structures, potentially eliminating the need for explicit noise conditioning. To this end, we develop a theoretical framework centered on Bernoulli edge-flip corruptions and extend it to encompass more complex scenarios involving coupled structure-attribute noise. Extensive empirical evaluations on both synthetic and real-world graph datasets, using models such as GDSS and DiGress, provide strong support for our theoretical findings. Notably, unconditional GDMs achieve performance comparable or superior to their conditioned counterparts, while also offering reductions in parameters (4-6%) and computation time (8-10%). Our results suggest that the high-dimensional nature of graph data itself often encodes sufficient information for the denoising process, opening avenues for simpler, more efficient GDM architectures.
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。