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 2510.23634cs.LGcs.AI
收藏

单调和可分离的集合函数:特征化与神经模型

Monotone and Separable Set Functions: Characterizations and Neural Models

IIT Bombay(印度理工学院班加罗尔分校);Technion(技术学院)

Soutrik Sarangi, Yonatan Sverdlov, Nadav Dym, Abir De

AI总结:

本文研究了保持集合自然偏序的集合到向量函数设计,提出弱MAS属性模型,展示了其在集合包含任务中的优势。

摘要:

受集合包含问题应用启发,本文考虑设计集合到向量函数,使自然偏序保持,即S⊆T当且仅当F(S)≤F(T)。我们称满足此性质的函数为单调和可分离(MAS)集合函数。我们建立了向量维度的上下界,作为多重集合基数和基础集大小的函数。在重要情况无限基础集时,我们证明MAS函数不存在,但提出名为our的模型,其满足弱MAS属性并具有Holder连续稳定性。我们还展示MAS函数可用于构建单调的通用模型,可近似所有单调集合函数。实验考虑了多种集合包含任务,结果显示我们的模型相比不考虑集合包含作为归纳偏置的标准集合模型具有优势。代码可在https://github.com/structlearning/MASNET获取。

英文摘要:

Motivated by applications for set containment problems, we consider the following fundamental problem: can we design set-to-vector functions so that the natural partial order on sets is preserved, namely $S\subseteq T \text{ if and only if } F(S)\leq F(T) $. We call functions satisfying this property Monotone and Separating (MAS) set functions. % We establish lower and upper bounds for the vector dimension necessary to obtain MAS functions, as a function of the cardinality of the multisets and the underlying ground set. In the important case of an infinite ground set, we show that MAS functions do not exist, but provide a model called our which provably enjoys a relaxed MAS property we name "weakly MAS" and is stable in the sense of Holder continuity. We also show that MAS functions can be used to construct universal models that are monotone by construction and can approximate all monotone set functions. Experimentally, we consider a variety of set containment tasks. The experiments show the benefit of using our our model, in comparison with standard set models which do not incorporate set containment as an inductive bias. Our code is available in https://github.com/structlearning/MASNET.

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。

↑