arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01654cs.AI
收藏

知识编译语言的有效解释

Efficient Explanations for Knowledge Compilation Languages

Université de Toulouse(图卢兹大学);Monash University(莫纳什大学);Université Paul Sabatier(保罗·萨巴蒂埃大学);IRIT(图卢兹计算机科学研究所);CNRS(法国国家科学研究中心)

Xuanxiang Huang, Yacine Izza, Alexey Ignatiev, Martin C. Cooper, Nicholas Asher, Joao Marques-Silva

摘要:

知识编译(KC)语言的实际用途越来越多,包括约束编程(CP)和机器学习(ML)。在大多数应用程序中,一个自然的问题是如何解释由KC语言表示的模型做出的决策。本文表明,许多最有名的KC语言,众所周知的类的解释可以计算在多项式时间。这些类包括确定性可分解否定范式(d-DNNF),以及任何严格不如d-DNNF简洁的KC语言。此外,本文还研究了解释的多项式时间计算可以推广到比d-DNNF更简洁的KC语言的条件。

英文摘要:

Knowledge compilation (KC) languages find a growing number of practical uses, including in Constraint Programming (CP) and in Machine Learning (ML). In most applications, one natural question is how to explain the decisions made by models represented by a KC language. This paper shows that for many of the best known KC languages, well-known classes of explanations can be computed in polynomial time. These classes include deterministic decomposable negation normal form (d-DNNF), and so any KC language that is strictly less succinct than d-DNNF. Furthermore, the paper also investigates the conditions under which polynomial time computation of explanations can be extended to KC languages more succinct than d-DNNF.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑