用信息论框架生成结构一致的新图，确保新颖性且可量化风险。
An Information Theoretic Framework for Graph Novelty Generation via Latent Mixture Modeling
- 在隐空间建模数据分布，通过混合模型判断新样本
- 生成的图既难被现有成分解释，又不影响整体结构
- 理论证明错误分类概率可收敛至零，适合安全场景
我们提出一种基于信息论的图新颖性生成框架，旨在生成与已有模式显著不同但保持全局结构一致的数据。方法将数据嵌入隐空间，使用有限混合模型建模隐分布，并基于描述长度定义新颖性和可靠性条件来生成新样本。新颖性要求生成样本无法被所有现有混合成分良好解释，可靠性则依据最小描述长度（MDL）原则限制其对整体混合结构的影响。理论上证明，合理设定阈值后，非新颖或不可靠样本的误分类概率可收敛至零并给出明确速率。在合成及基准图数据集上的实验表明，该方法实现了可量化的风险控制，支持有原则的新颖性生成。
原文摘要 · Abstract (English)
We propose an information-theoretic framework for graph novelty generation, which aims to generate data that are distinct from existing patterns while preserving global structural consistency. Our approach embeds data into a latent space, models the latent distribution using finite mixture models, and generates novel samples by imposing explicit novelty and reliability conditions formulated in terms of description length. Specifically, novelty is enforced by requiring generated samples to be poorly explained by all existing mixture components, while reliability constrains their impact on the overall mixture structure under the Minimum Description Length (MDL) principle. We provide a theoretical analysis showing that, with appropriate threshold choices, the probabilities of misclassifying non-novel or unreliable samples converge to zero with explicit rates. Experiments on synthetic and benchmark graph datasets demonstrate that the proposed method enables principled novelty generation with quantifiable risk.
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。