# Learning logic programs by discovering higher-order abstractions

arXiv: https://arxiv.org/abs/2308.08334 · HTML: https://mlsanity.com/paper/2308.08334/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 62 references that are in the map.
- First posted on arXiv 16 Aug 2023.

## Builds on (most cited first, 16 of 16)

- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [Predicate Invention for Bilevel Planning](https://mlsanity.com/paper/2203.09634/) (2022)
- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Abductive Knowledge Induction From Raw Data](https://mlsanity.com/paper/2010.03514/) (2020)
- [Making sense of sensory input](https://mlsanity.com/paper/1910.02227/) (2019)
- [babble: Learning Better Abstractions with E-Graphs and Anti-Unification](https://mlsanity.com/paper/2212.04596/) (2022)
- [Logical reduction of metarules](https://mlsanity.com/paper/1907.10952/) (2019)
- [Learning Higher-Order Programs without Meta-Interpretive Learning](https://mlsanity.com/paper/2112.14603/) (2021)
- [Learning Relational Representations with Auto-encoding Logic Programs](https://mlsanity.com/paper/1903.12577/) (2019)
- [Learning higher-order logic programs](https://mlsanity.com/paper/1907.10953/) (2019)
- [Constraint-driven multi-task learning](https://mlsanity.com/paper/2208.11656/) (2022)

## Built on by (most cited first, 1 of 1)

- [Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy](https://mlsanity.com/paper/2509.00961/) (2025)

## Abstract (arXiv)

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.