Graph Neural Networks for Scheduling of SMT Solvers

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F21%3AA2402MER" target="_blank" >RIV/61988987:17610/21:A2402MER - isvavai.cz</a>
Alternative codes found
RIV/68407700:21730/21:00353755
Result on the web
<a href="https://ieeexplore.ieee.org/document/9643296" target="_blank" >https://ieeexplore.ieee.org/document/9643296</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICTAI52525.2021.00072" target="_blank" >10.1109/ICTAI52525.2021.00072</a>

Result language
angličtina
Original language name
Graph Neural Networks for Scheduling of SMT Solvers
Original language description
This paper develops an approach to the scheduling of solvers in the domain of Satisfiability Modulo Theories (SMT) using a Graph Neural Network (GNN). In contrast to related methods, GNNs do not require manual feature design as they enable discovering relevant features in the raw data. We train them to predict the effectivity of individual solvers on a given problem. Rather than choosing only one solver with the best prediction, we schedule the solvers by ordering them according to the predicted runtime and dividing the overall runtime into all solvers uniformly. We compare our approach to several baselines. In the selected benchmarks, we show a substantial improvement over these baselines in terms of the number of solved problems and overall solving time.
Czech name
—
Czech description
—

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
2021 IEEE 33RD INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2021)
ISBN
978-1-6654-0898-1
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
447-451
Publisher name
IEEE
Place of publication
Los Alamitos, USA
Event location
Online
Event date
Nov 1, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000747482300064

Similar results(10)