A cross-attention context layer on top of graph neural networks yields small accuracy gains and uncertainty estimates for graph-level classification and regression.
The prediction of the quality of results in logic synthesis using transformer and graph neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
A cross-attention context layer on top of graph neural networks yields small accuracy gains and uncertainty estimates for graph-level classification and regression.