ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and rule recovery on probabilistic ILP benchmarks.
Training Acc: 0.8754 | Eval Acc: 0.8677 Val Coverage: (N_b=127, N_r=102, N_r/N_b=0.8031) Train Coverage: (N_b=2813, N_r=2250, N_r/N_b=0.7999)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming
ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and rule recovery on probabilistic ILP benchmarks.