# Forgetting to learn logic programs

arXiv: https://arxiv.org/abs/1911.06643 · HTML: https://mlsanity.com/paper/1911.06643/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Learning Higher-Order Programs without Meta-Interpretive Learning](https://mlsanity.com/paper/2112.14603/) (2021)
- [Learning Logic Programs From Noisy Failures](https://mlsanity.com/paper/2201.03702/) (2021)
- [Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments](https://mlsanity.com/paper/2309.03651/) (2023)
- [Constraint-driven multi-task learning](https://mlsanity.com/paper/2208.11656/) (2022)
- [Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming](https://mlsanity.com/paper/2407.14714/) (2024)
- [Preprocessing in Inductive Logic Programming](https://mlsanity.com/paper/2112.12551/) (2021)
- [ADVENT: LLM-Driven Automatic Predicate Invention for ILP](https://mlsanity.com/paper/2607.01585/) (2026)

## Abstract (arXiv)

Most program induction approaches require predefined, often hand-engineered, background knowledge (BK). To overcome this limitation, we explore methods to automatically acquire BK through multi-task learning. In this approach, a learner adds learned programs to its BK so that they can be reused to help learn other programs. To improve learning performance, we explore the idea of forgetting, where a learner can additionally remove programs from its BK. We consider forgetting in an inductive logic programming (ILP) setting. We show that forgetting can significantly reduce both the size of the hypothesis space and the sample complexity of an ILP learner. We introduce Forgetgol, a multi-task ILP learner which supports forgetting. We experimentally compare Forgetgol against approaches that either remember or forget everything. Our experimental results show that Forgetgol outperforms the alternative approaches when learning from over 10,000 tasks.