arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.09381cs.LOcs.AIcs.DB
收藏

机器学习模型的查询语言

Query Languages for Machine-Learning Models

RWTH Aachen University(亚琛工业大学)

Martin Grohe

AI总结:

本文提出了一种用于神经网络的查询语言,基于加权图结构,探讨了FO(SUM)和IFP(SUM)的表达力和计算复杂性。

摘要:

本文讨论了两种用于加权有限结构的逻辑:带有求和的一阶逻辑(FO(SUM))及其递归扩展IFP(SUM)。这些逻辑起源于1990年代Grädel、Gurevich和Meer的基础性工作。在与Standke、Steegmans和Van den Bussche的联合工作中,我们研究了这些逻辑作为机器学习模型(特别是神经网络)的查询语言,因为神经网络自然地表示为加权图。我展示了可以使用这些逻辑表达的神经网络查询示例,并讨论了它们的表达力和计算复杂性。

英文摘要:

In this paper, I discuss two logics for weighted finite structures: first-order logic with summation (FO(SUM)) and its recursive extension IFP(SUM). These logics originate from foundational work by Grädel, Gurevich, and Meer in the 1990s. In recent joint work with Standke, Steegmans, and Van den Bussche, we have investigated these logics as query languages for machine learning models, specifically neural networks, which are naturally represented as weighted graphs. I present illustrative examples of queries to neural networks that can be expressed in these logics and discuss fundamental results on their expressiveness and computational complexity.

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。

↑