Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313366927> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313366927 endingPage "31" @default.
- W4313366927 startingPage "29" @default.
- W4313366927 abstract "The recent work ``Combinatorial Optimization with Physics-Inspired Graph Neural Networks'' [Nat Mach Intell 4 (2022) 367] introduces a physics-inspired unsupervised Graph Neural Network (GNN) to solve combinatorial optimization problems on sparse graphs. To test the performances of these GNNs, the authors of the work show numerical results for two fundamental problems: maximum cut and maximum independent set (MIS). They conclude that the graph neural network optimizer performs on par or outperforms existing solvers, with the ability to scale beyond the state of the art to problems with millions of variables. In this comment, we show that a simple greedy algorithm, running in almost linear time, can find solutions for the MIS problem of much better quality than the GNN. The greedy algorithm is faster by a factor of $10^4$ with respect to the GNN for problems with a million variables. We do not see any good reason for solving the MIS with these GNN, as well as for using a sledgehammer to crack nuts. In general, many claims of superiority of neural networks in solving combinatorial problems are at risk of being not solid enough, since we lack standard benchmarks based on really hard problems. We propose one of such hard benchmarks, and we hope to see future neural network optimizers tested on these problems before any claim of superiority is made." @default.
- W4313366927 created "2023-01-06" @default.
- W4313366927 creator A5032395277 @default.
- W4313366927 creator A5056141397 @default.
- W4313366927 date "2022-12-30" @default.
- W4313366927 modified "2023-09-30" @default.
- W4313366927 title "Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set" @default.
- W4313366927 cites W1979720612 @default.
- W4313366927 cites W2014810204 @default.
- W4313366927 cites W2042503074 @default.
- W4313366927 cites W2083116175 @default.
- W4313366927 cites W2089247135 @default.
- W4313366927 cites W2787305781 @default.
- W4313366927 cites W2933344818 @default.
- W4313366927 cites W2962704928 @default.
- W4313366927 cites W2997090216 @default.
- W4313366927 cites W3047863327 @default.
- W4313366927 cites W3181036294 @default.
- W4313366927 cites W3188522200 @default.
- W4313366927 cites W3189470799 @default.
- W4313366927 cites W4306652901 @default.
- W4313366927 doi "https://doi.org/10.1038/s42256-022-00589-y" @default.
- W4313366927 hasPublicationYear "2022" @default.
- W4313366927 type Work @default.
- W4313366927 citedByCount "2" @default.
- W4313366927 countsByYear W43133669272022 @default.
- W4313366927 countsByYear W43133669272023 @default.
- W4313366927 crossrefType "journal-article" @default.
- W4313366927 hasAuthorship W4313366927A5032395277 @default.
- W4313366927 hasAuthorship W4313366927A5056141397 @default.
- W4313366927 hasBestOaLocation W43133669272 @default.
- W4313366927 hasConcept C11413529 @default.
- W4313366927 hasConcept C122818955 @default.
- W4313366927 hasConcept C126255220 @default.
- W4313366927 hasConcept C132525143 @default.
- W4313366927 hasConcept C137836250 @default.
- W4313366927 hasConcept C154945302 @default.
- W4313366927 hasConcept C177264268 @default.
- W4313366927 hasConcept C199360897 @default.
- W4313366927 hasConcept C33923547 @default.
- W4313366927 hasConcept C41008148 @default.
- W4313366927 hasConcept C50644808 @default.
- W4313366927 hasConcept C51823790 @default.
- W4313366927 hasConcept C52692508 @default.
- W4313366927 hasConcept C80444323 @default.
- W4313366927 hasConceptScore W4313366927C11413529 @default.
- W4313366927 hasConceptScore W4313366927C122818955 @default.
- W4313366927 hasConceptScore W4313366927C126255220 @default.
- W4313366927 hasConceptScore W4313366927C132525143 @default.
- W4313366927 hasConceptScore W4313366927C137836250 @default.
- W4313366927 hasConceptScore W4313366927C154945302 @default.
- W4313366927 hasConceptScore W4313366927C177264268 @default.
- W4313366927 hasConceptScore W4313366927C199360897 @default.
- W4313366927 hasConceptScore W4313366927C33923547 @default.
- W4313366927 hasConceptScore W4313366927C41008148 @default.
- W4313366927 hasConceptScore W4313366927C50644808 @default.
- W4313366927 hasConceptScore W4313366927C51823790 @default.
- W4313366927 hasConceptScore W4313366927C52692508 @default.
- W4313366927 hasConceptScore W4313366927C80444323 @default.
- W4313366927 hasIssue "1" @default.
- W4313366927 hasLocation W43133669271 @default.
- W4313366927 hasLocation W43133669272 @default.
- W4313366927 hasLocation W43133669273 @default.
- W4313366927 hasOpenAccess W4313366927 @default.
- W4313366927 hasPrimaryLocation W43133669271 @default.
- W4313366927 hasRelatedWork W128408443 @default.
- W4313366927 hasRelatedWork W1560987333 @default.
- W4313366927 hasRelatedWork W1994389641 @default.
- W4313366927 hasRelatedWork W2054195159 @default.
- W4313366927 hasRelatedWork W2113677211 @default.
- W4313366927 hasRelatedWork W2114616060 @default.
- W4313366927 hasRelatedWork W2999460072 @default.
- W4313366927 hasRelatedWork W3171554204 @default.
- W4313366927 hasRelatedWork W4200602616 @default.
- W4313366927 hasRelatedWork W4282006399 @default.
- W4313366927 hasVolume "5" @default.
- W4313366927 isParatext "false" @default.
- W4313366927 isRetracted "false" @default.
- W4313366927 workType "article" @default.