Research map / Learning theory and algorithms / Combinatorial and search optimization
Generalisation through Negation and Predicate Invention
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces NOPI, an ILP system combining negation and predicate invention to learn rules with universally quantified body-only variables; the provided text is only the AAAI formatting template, so the paper's results are not available.
Problem
Generalising from few examples in inductive logic programming, where rules need universally quantified body-only variables.
Approach
Combine negation and predicate invention in an ILP system so that learned rules can contain universally quantified body-only variables, improving generalisation.
Closest papers by meaning
- Learn to Explain Efficiently via Neural Logic Inductive Learning (ICLR 2020 · similarity 0.88)
- Neural Logic Machines (ICLR 2019 · similarity 0.86)
- Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis (AAAI 2025 · similarity 0.85)
- Differentiable Rule Induction from Raw Sequence Inputs (ICLR 2025 · similarity 0.83)
- Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI (NeurIPS 2025 · similarity 0.83)
- Large Language Models are Interpretable Learners (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.