A graph-to-sequence transformer predicts control structures for chemical flowsheets, achieving 73.2% top-5 accuracy on 10,000 synthetic examples and outperforming sequence-based models in small-data regimes.
S., Caballero, M., and Schweidtmann, A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence
A graph-to-sequence transformer predicts control structures for chemical flowsheets, achieving 73.2% top-5 accuracy on 10,000 synthetic examples and outperforming sequence-based models in small-data regimes.