Assur-KB：机构设计的可组合表示与高效学习研究
Efficient Learning of Mechanism Designs and Compositionality
AI 导读
arXiv 论文提出 Assur-KB 表示方法，将平面机构分解为不可约模块、边界接口和求解依赖关系。实验显示其特征在 50-10,000 个机构的训练预算下实现几何平均 1.8 倍的样本效率优势，并在关节重标记下保持不变性、在成对组合下获得更高有效生成率，结构索引覆盖 1002 万个机构。理论结果刻画了接口信息缺失和敏感性累积带来的物理极限。
正文 · 原文
Abstract:Learning mechanism behaviour requires a representation of how connected parts jointly constrain motion. We study whether exposing reusable constraint subassemblies improves prediction from limited data. Assur-KB represents planar mechanisms through irreducible modules, boundary interfaces, and solve dependencies while retaining source geometry. Our theoretical results characterize transfer through module interfaces and establish physical limits arising from missing interface information and accumulated sensitivity. To test the representation claim directly, the experimental design compares matched mechanism-curve pairs across training budgets within the same multilayer-perceptron family. This controlled comparison establishes the utility of the complete representation in the evaluated learning setting. Assur-derived features provide a geometric-mean $1.8\times$ advantage in sample efficiency over flattened adjacency and position inputs across budgets of 50-10,000 mechanisms. Separate experiments establish invariance under tested joint relabelings, higher valid-generation rates under dyadic composition, and a coarser structural index over 10.02 million mechanisms. In summary, the theory and experiments identify how physical constraint structure supports limited-data prediction and which interface conditions govern compositional reuse.
| Subjects: | Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2610.40005 [cs.AI] |
| (or arXiv:2610.40005v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40005 arXiv-issued DOI via DataCite |
Submission history
From: João Pedro Gandarela [view email]
[v1]
Thu, 29 Oct 2026 13:23:44 UTC (806 KB)
来源：arXiv cs.AI · arxiv.org