paper-with-me

Papers

Knowledge Refactoring for Inductive Program Synthesis

2020-04-21 · Sebastijan Dumancic, Tias Guns, Andrew Cropper

Humans constantly restructure knowledge to use it more efficiently. Our goal is to give a machine learning system similar abilities so that it can learn more efficiently. We introduce the \textit{knowledge refactoring} problem, where the goal is to restructure a learner's knowledge base to reduce its size and to minimise redundancy in it. We focus on inductive logic programming, where the knowledge base is a logic program. We introduce Knorf, a system which solves the refactoring problem using constraint optimisation. We evaluate our approach on two program induction domains: real-world string transformations and building Lego structures. Our experiments show that learning from refactored knowledge can improve predictive accuracies fourfold and reduce learning times by half.

📄 PDF Abstract BibTeX arXiv:2004.09931

Code (1)

sebdumancic/knorf_aaai21 공식 구현

Tasks

Inductive logic programmingProgram inductionProgram Synthesis

Similar Papers 제목 키워드 기반

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 formula…

Inductive logic programmingProgram SynthesisVisual Reasoning

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

2023-10-30 · Gabriel Grand, Lionel Wong, Maddy Bowers, Theo X. Olausson 외

While large language models (LLMs) now excel at code generation, a key aspect of software development is the art of refactoring: consolidating code into libraries of reusable and readable programs. In this paper, we intr…

Code GenerationProgram Synthesis

AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance

2026-06-29 · Yang Zou, Zijian Ding, Yizhou Sun, Jason Cong arxiv

High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between softwar…

Scalable Knowledge Refactoring using Constrained Optimisation

2024-08-21 · Minghao Liu, David M. Cerna, Filipe Gouveia, Andrew Cropper

Knowledge refactoring compresses a logic program by introducing new rules. Current approaches struggle to scale to large programs. To overcome this limitation, we introduce a constrained optimisation refactoring approach…

Are There Good Mistakes? A Theoretical Analysis of CEGIS

2014-07-21 · Susmit Jha, Sanjit A. Seshia

Counterexample-guided inductive synthesis CEGIS is used to synthesize programs from a candidate space of programs. The technique is guaranteed to terminate and synthesize the correct program if the space of candidate pro…