SEAL makes GNN predictions inherently interpretable by decomposing molecules into fragments and defining the prediction as a sum of per-fragment contributions, enforced with regularized fragment-local message passing.
C.; Boukouvalas, Z.; Fuge, M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis
SEAL makes GNN predictions inherently interpretable by decomposing molecules into fragments and defining the prediction as a sum of per-fragment contributions, enforced with regularized fragment-local message passing.