Research
Pricing Symbolic Rules by What GNNs Leave Unlearned
This paper proposes an information-theoretic framework for evaluating symbolic rules added to graph neural networks, measuring the exact log-loss reduction a rule can provide given what the model family computes. The authors show that rule design can be treated as rule discovery, scoring candidates on the network's out-of-fold residual against calibrated permutation nulls. On ZINC, the method recovers a hidden ring term and beats expert cycle counts, and on BBBP it significantly outperforms both the plain network and the expert rule.
graph neural networkssymbolic knowledgerule discovery