paper-with-me

Papers

Learning logic programs by discovering higher-order abstractions

2023-08-16 · Céline Hocquette, Sebastijan Dumančić, Andrew Cropper

We introduce the higher-order refactoring problem, where the goal is to compress a logic program by discovering higher-order abstractions, such as map, filter, and fold. We implement our approach in Stevie, which formulates the refactoring problem as a constraint optimisation problem. Our experiments on multiple domains, including program synthesis and visual reasoning, show that refactoring can improve the learning performance of an inductive logic programming system, specifically improving predictive accuracies by 27% and reducing learning times by 47%. We also show that Stevie can discover abstractions that transfer to multiple domains.

📄 PDF Abstract BibTeX arXiv:2308.08334

Code (1)

celinehocquette/ijcai24-stevie 공식 구현

Tasks

Inductive logic programmingProgram SynthesisVisual Reasoning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives

2023-05-09 · R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie

Programs are an increasingly popular representation for visual data, exposing compact, interpretable structure that supports manipulation. Visual programs are usually written in domain-specific languages (DSLs). Finding …

Learning higher-order logic programs

2019-07-25 · Andrew Cropper, Rolf Morel, Stephen H. Muggleton

A key feature of inductive logic programming (ILP) is its ability to learn first-order programs, which are intrinsically more expressive than propositional programs. In this paper, we introduce techniques to learn higher…

Inductive logic programming

The Stable Model Semantics for Higher-Order Logic Programming

2024-08-20 · Bart Bogaerts, Angelos Charalambidis, Giannos Chatziagapis, Babis Kostopoulos 외

We propose a stable model semantics for higher-order logic programs. Our semantics is developed using Approximation Fixpoint Theory (AFT), a powerful formalism that has successfully been used to give meaning to diverse n…

Learning Higher-Order Programs without Meta-Interpretive Learning

2021-12-29 · Stanisław J. Purgał, David M. Cerna, Cezary Kaliszyk

Learning complex programs through inductive logic programming (ILP) remains a formidable challenge. Existing higher-order enabled ILP systems show improved accuracy and learning performance, though remain hampered by the…

Inductive logic programming

Top-Down Synthesis for Library Learning

2022-11-29 · Matthew Bowers, Theo X. Olausson, Lionel Wong, Gabriel Grand 외

This paper introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL). The algorithm buil…