Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387293723> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4387293723 abstract "Recent advancements in combinatorial optimization (CO) problems emphasize the potential of graph neural networks (GNNs). The physics-inspired GNN (PI-GNN) solver, which finds approximate solutions through unsupervised learning, has attracted significant attention for large-scale CO problems. Nevertheless, there has been limited discussion on the performance of the PI-GNN solver for CO problems on relatively dense graphs where the performance of greedy algorithms worsens. In addition, since the PI-GNN solver employs a relaxation strategy, an artificial transformation from the continuous space back to the original discrete space is necessary after learning, potentially undermining the robustness of the solutions. This paper numerically demonstrates that the PI-GNN solver can be trapped in a local solution, where all variables are zero, in the early stage of learning for CO problems on the dense graphs. Then, we address these problems by controlling the continuity and discreteness of relaxed variables while avoiding the local solution: (i) introducing a new penalty term that controls the continuity and discreteness of the relaxed variables and eliminates the local solution; (ii) proposing a new continuous relaxation annealing (CRA) strategy. This new annealing first prioritizes continuous solutions and intensifies exploration by leveraging the continuity while avoiding the local solution and then schedules the penalty term for prioritizing a discrete solution until the relaxed variables are almost discrete values, which eliminates the need for an artificial transformation from the continuous to the original discrete space. Empirically, better results are obtained for CO problems on the dense graphs, where the PI-GNN solver struggles to find reasonable solutions, and for those on relatively sparse graphs. Furthermore, the computational time scaling is identical to that of the PI-GNN solver." @default.
- W4387293723 created "2023-10-03" @default.
- W4387293723 creator A5088334998 @default.
- W4387293723 date "2023-09-29" @default.
- W4387293723 modified "2023-10-04" @default.
- W4387293723 title "Controlling Continuous Relaxation for Combinatorial Optimization" @default.
- W4387293723 doi "https://doi.org/10.48550/arxiv.2309.16965" @default.
- W4387293723 hasPublicationYear "2023" @default.
- W4387293723 type Work @default.
- W4387293723 citedByCount "0" @default.
- W4387293723 crossrefType "posted-content" @default.
- W4387293723 hasAuthorship W4387293723A5088334998 @default.
- W4387293723 hasBestOaLocation W43872937231 @default.
- W4387293723 hasConcept C104317684 @default.
- W4387293723 hasConcept C126255220 @default.
- W4387293723 hasConcept C126980161 @default.
- W4387293723 hasConcept C134306372 @default.
- W4387293723 hasConcept C137836250 @default.
- W4387293723 hasConcept C153782549 @default.
- W4387293723 hasConcept C15744967 @default.
- W4387293723 hasConcept C185592680 @default.
- W4387293723 hasConcept C204241405 @default.
- W4387293723 hasConcept C2776029896 @default.
- W4387293723 hasConcept C2778770139 @default.
- W4387293723 hasConcept C3019612716 @default.
- W4387293723 hasConcept C33923547 @default.
- W4387293723 hasConcept C41008148 @default.
- W4387293723 hasConcept C55493867 @default.
- W4387293723 hasConcept C77805123 @default.
- W4387293723 hasConceptScore W4387293723C104317684 @default.
- W4387293723 hasConceptScore W4387293723C126255220 @default.
- W4387293723 hasConceptScore W4387293723C126980161 @default.
- W4387293723 hasConceptScore W4387293723C134306372 @default.
- W4387293723 hasConceptScore W4387293723C137836250 @default.
- W4387293723 hasConceptScore W4387293723C153782549 @default.
- W4387293723 hasConceptScore W4387293723C15744967 @default.
- W4387293723 hasConceptScore W4387293723C185592680 @default.
- W4387293723 hasConceptScore W4387293723C204241405 @default.
- W4387293723 hasConceptScore W4387293723C2776029896 @default.
- W4387293723 hasConceptScore W4387293723C2778770139 @default.
- W4387293723 hasConceptScore W4387293723C3019612716 @default.
- W4387293723 hasConceptScore W4387293723C33923547 @default.
- W4387293723 hasConceptScore W4387293723C41008148 @default.
- W4387293723 hasConceptScore W4387293723C55493867 @default.
- W4387293723 hasConceptScore W4387293723C77805123 @default.
- W4387293723 hasLocation W43872937231 @default.
- W4387293723 hasOpenAccess W4387293723 @default.
- W4387293723 hasPrimaryLocation W43872937231 @default.
- W4387293723 hasRelatedWork W1646136891 @default.
- W4387293723 hasRelatedWork W174808068 @default.
- W4387293723 hasRelatedWork W2031052090 @default.
- W4387293723 hasRelatedWork W2065487957 @default.
- W4387293723 hasRelatedWork W2122227724 @default.
- W4387293723 hasRelatedWork W2340945706 @default.
- W4387293723 hasRelatedWork W2770229024 @default.
- W4387293723 hasRelatedWork W4280588714 @default.
- W4387293723 hasRelatedWork W4285891591 @default.
- W4387293723 hasRelatedWork W288436476 @default.
- W4387293723 isParatext "false" @default.
- W4387293723 isRetracted "false" @default.
- W4387293723 workType "article" @default.