A canonical decoder that reads literal scores yields exactly equivariant discrete DNF rules under the full rule-induction symmetry group, letting a small-data pretrained inducer transfer to schemas of up to 1024 atoms.
Inductive Logic Programming: Theory and Methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pretrain on Small Synthetic Data, Scale Large for Free: Symmetry-Aware Foundation Model for Logic Rule Induction
A canonical decoder that reads literal scores yields exactly equivariant discrete DNF rules under the full rule-induction symmetry group, letting a small-data pretrained inducer transfer to schemas of up to 1024 atoms.