让模拟轨迹生成更符合系统结构约束，避免生成不合理的未来场景。
Learning and Structurally Validating Simulation Scenario Continuations in Dynamic Graph Systems
- 用条件扩散模型生成未来图状态，再通过符号层验证结构合理性。
- 硬过滤可清除所有无效场景，保留84.4%有效生成结果。
- 适合需要高可靠性模拟的复杂系统建模与决策支持场景。
数据驱动的生成模型可将部分观测的模拟轨迹扩展为多个未来场景集合。然而，与学习到的轨迹分布一致，并不保证生成的延续满足模拟系统的结构条件。本文提出一种动态图模拟中场景延续的联合学习与后生成结构验证方法。基于条件扩散模型从部分历史生成未来图状态轨迹，外部符号层使用布尔可接受性指标和连续违反分数评估每条延续。该信息用于硬过滤与软加权，可选投影作为确定性修复基线。方法在两个共享相同延续架构与训练协议但维度与依赖复杂度不同的受控动态图环境中评估。评估涵盖无效概率质量、场景保留率、有效样本量、多样性、鲁棒性与校准性。在紧凑正控环境下，未约束的无效质量为0.002996，表明学习与可接受场景空间近乎重合；在中等复杂度环境下，无效质量升至0.155929。硬过滤消除所有无效场景，同时保留84.4%的生成延续。软加权保持有效样本量比0.998764，但仅将无效质量降至0.148807。结果表明，学习分布支持、结构可接受性与概率校准可能偏离，应分别评估。
原文摘要 · Abstract (English)
Data-driven generative models can extend partially observed simulation trajectories into ensembles of alternative future scenarios. However, consistency with a learned trajectory distribution does not ensure that generated continuations satisfy the structural conditions of the simulated system. This paper presents a method for learned scenario continuation and post-generation structural validation in dynamic graph simulations. A conditional diffusion model generates future graph-state trajectories from partial histories, while an external symbolic layer evaluates each continuation using a Boolean admissibility indicator and a continuous violation score. This information supports hard filtering and soft weighting, with optional projection considered as a deterministic repair baseline. The method is evaluated on two controlled dynamic-graph regimes sharing the same continuation architecture and training protocol but differing in dimensionality and dependency complexity. Evaluation considers invalid probability mass, scenario retention, effective sample size, diversity, robustness, and calibration. In the compact positive-control regime, unconstrained invalid mass is 0.002996, indicating near-complete overlap between the learned and admissible scenario spaces. In the medium-complexity regime, invalid mass rises to 0.155929. Hard filtering removes all invalid scenarios while retaining 84.4% of generated continuations. Soft weighting preserves an effective sample size ratio of 0.998764 but reduces invalid mass only to 0.148807. These results show that learned-distribution support, structural admissibility, and probability calibration can diverge and should therefore be assessed separately in learned simulation-scenario generation and management.
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。