A study of the learnability of relational properties: model counting meets machine learning (MCML)

Muhammad Usman, Wenxi Wang, Kaiyuan Wang, Marko Vasic, H. Vikalo, S. Khurshid
{"title":"A study of the learnability of relational properties: model counting meets machine learning (MCML)","authors":"Muhammad Usman, Wenxi Wang, Kaiyuan Wang, Marko Vasic, H. Vikalo, S. Khurshid","doi":"10.1145/3385412.3386015","DOIUrl":null,"url":null,"abstract":"This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire (bounded) input spaces, and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art model counters. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1-score) when evaluated in the common setting of using training and test datasets -- even when the training dataset is much smaller than the test dataset -- indicating the seeming simplicity of learning relational properties. However, MCML metrics based on model counting show that the performance can degrade substantially when tested against the entire (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true performance.","PeriodicalId":20580,"journal":{"name":"Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation","volume":"573 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2019-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3385412.3386015","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire (bounded) input spaces, and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art model counters. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1-score) when evaluated in the common setting of using training and test datasets -- even when the training dataset is much smaller than the test dataset -- indicating the seeming simplicity of learning relational properties. However, MCML metrics based on model counting show that the performance can degrade substantially when tested against the entire (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true performance.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
关系属性的可学习性研究:模型计数与机器学习(MCML)
本文介绍了用MCML方法对关系属性的可学习性进行实证研究,这些关系属性可以用著名的软件设计语言Alloy来表示。MCML的一个关键新颖之处在于对经过训练的机器学习(ML)模型(特别是决策树)的性能和语义差异进行量化,这些模型相对于整个(有界的)输入空间,而不仅仅是针对给定的训练和测试数据集(这是常见的做法)。MCML将量化问题简化为模型计数的经典复杂性理论问题,并采用了最先进的模型计数器。结果表明,在使用训练和测试数据集的常见设置中进行评估时,相对简单的ML模型可以获得惊人的高性能(准确性和f1分数)——即使训练数据集比测试数据集小得多——这表明学习关系属性似乎很简单。然而,基于模型计数的MCML指标表明,当针对整个(有界)输入空间进行测试时,性能会大幅下降,这表明精确学习这些属性的复杂性很高,以及模型计数在量化真实性能方面的有用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Type error feedback via analytic program repair Inductive sequentialization of asynchronous programs Decidable verification under a causally consistent shared memory SympleGraph: distributed graph processing with precise loop-carried dependency guarantee Debug information validation for optimized code
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1