Zeno Kujawa, John Poole, Dobrik Georgiev, Danilo Numeroso, Pietro Liò
{"title":"Neural Algorithmic Reasoning with Multiple Correct Solutions","authors":"Zeno Kujawa, John Poole, Dobrik Georgiev, Danilo Numeroso, Pietro Liò","doi":"arxiv-2409.06953","DOIUrl":null,"url":null,"abstract":"Neural Algorithmic Reasoning (NAR) aims to optimize classical algorithms.\nHowever, canonical implementations of NAR train neural networks to return only\na single solution, even when there are multiple correct solutions to a problem,\nsuch as single-source shortest paths. For some applications, it is desirable to\nrecover more than one correct solution. To that end, we give the first method\nfor NAR with multiple solutions. We demonstrate our method on two classical\nalgorithms: Bellman-Ford (BF) and Depth-First Search (DFS), favouring deeper\ninsight into two algorithms over a broader survey of algorithms. This method\ninvolves generating appropriate training data as well as sampling and\nvalidating solutions from model output. Each step of our method, which can\nserve as a framework for neural algorithmic reasoning beyond the tasks\npresented in this paper, might be of independent interest to the field and our\nresults represent the first attempt at this task in the NAR literature.","PeriodicalId":501301,"journal":{"name":"arXiv - CS - Machine Learning","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06953","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Neural Algorithmic Reasoning (NAR) aims to optimize classical algorithms.
However, canonical implementations of NAR train neural networks to return only
a single solution, even when there are multiple correct solutions to a problem,
such as single-source shortest paths. For some applications, it is desirable to
recover more than one correct solution. To that end, we give the first method
for NAR with multiple solutions. We demonstrate our method on two classical
algorithms: Bellman-Ford (BF) and Depth-First Search (DFS), favouring deeper
insight into two algorithms over a broader survey of algorithms. This method
involves generating appropriate training data as well as sampling and
validating solutions from model output. Each step of our method, which can
serve as a framework for neural algorithmic reasoning beyond the tasks
presented in this paper, might be of independent interest to the field and our
results represent the first attempt at this task in the NAR literature.