Arnaud Deza, Elias B. Khalil, Zhenan Fan, Zirui Zhou, Yong Zhang
{"title":"Learn2Aggregate:使用图神经网络监督生成 Chvátal-Gomory 剪切","authors":"Arnaud Deza, Elias B. Khalil, Zhenan Fan, Zirui Zhou, Yong Zhang","doi":"arxiv-2409.06559","DOIUrl":null,"url":null,"abstract":"We present $\\textit{Learn2Aggregate}$, a machine learning (ML) framework for\noptimizing the generation of Chv\\'atal-Gomory (CG) cuts in mixed integer linear\nprogramming (MILP). The framework trains a graph neural network to classify\nuseful constraints for aggregation in CG cut generation. The ML-driven CG\nseparator selectively focuses on a small set of impactful constraints,\nimproving runtimes without compromising the strength of the generated cuts. Key\nto our approach is the formulation of a constraint classification task which\nfavours sparse aggregation of constraints, consistent with empirical findings.\nThis, in conjunction with a careful constraint labeling scheme and a hybrid of\ndeep learning and feature engineering, results in enhanced CG cut generation\nacross five diverse MILP benchmarks. On the largest test sets, our method\ncloses roughly $\\textit{twice}$ as much of the integrality gap as the standard\nCG method while running 40$% faster. This performance improvement is due to our\nmethod eliminating 75% of the constraints prior to aggregation.","PeriodicalId":501286,"journal":{"name":"arXiv - MATH - Optimization and Control","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learn2Aggregate: Supervised Generation of Chvátal-Gomory Cuts Using Graph Neural Networks\",\"authors\":\"Arnaud Deza, Elias B. Khalil, Zhenan Fan, Zirui Zhou, Yong Zhang\",\"doi\":\"arxiv-2409.06559\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present $\\\\textit{Learn2Aggregate}$, a machine learning (ML) framework for\\noptimizing the generation of Chv\\\\'atal-Gomory (CG) cuts in mixed integer linear\\nprogramming (MILP). The framework trains a graph neural network to classify\\nuseful constraints for aggregation in CG cut generation. The ML-driven CG\\nseparator selectively focuses on a small set of impactful constraints,\\nimproving runtimes without compromising the strength of the generated cuts. Key\\nto our approach is the formulation of a constraint classification task which\\nfavours sparse aggregation of constraints, consistent with empirical findings.\\nThis, in conjunction with a careful constraint labeling scheme and a hybrid of\\ndeep learning and feature engineering, results in enhanced CG cut generation\\nacross five diverse MILP benchmarks. On the largest test sets, our method\\ncloses roughly $\\\\textit{twice}$ as much of the integrality gap as the standard\\nCG method while running 40$% faster. This performance improvement is due to our\\nmethod eliminating 75% of the constraints prior to aggregation.\",\"PeriodicalId\":501286,\"journal\":{\"name\":\"arXiv - MATH - Optimization and Control\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - MATH - Optimization and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06559\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - MATH - Optimization and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06559","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Learn2Aggregate: Supervised Generation of Chvátal-Gomory Cuts Using Graph Neural Networks
We present $\textit{Learn2Aggregate}$, a machine learning (ML) framework for
optimizing the generation of Chv\'atal-Gomory (CG) cuts in mixed integer linear
programming (MILP). The framework trains a graph neural network to classify
useful constraints for aggregation in CG cut generation. The ML-driven CG
separator selectively focuses on a small set of impactful constraints,
improving runtimes without compromising the strength of the generated cuts. Key
to our approach is the formulation of a constraint classification task which
favours sparse aggregation of constraints, consistent with empirical findings.
This, in conjunction with a careful constraint labeling scheme and a hybrid of
deep learning and feature engineering, results in enhanced CG cut generation
across five diverse MILP benchmarks. On the largest test sets, our method
closes roughly $\textit{twice}$ as much of the integrality gap as the standard
CG method while running 40$% faster. This performance improvement is due to our
method eliminating 75% of the constraints prior to aggregation.