TY - JOUR AU - Cropper, Andrew PY - 2020/04/03 Y2 - 2024/03/28 TI - Forgetting to Learn Logic Programs JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 34 IS - 04 SE - AAAI Technical Track: Machine Learning DO - 10.1609/aaai.v34i04.5776 UR - https://ojs.aaai.org/index.php/AAAI/article/view/5776 SP - 3676-3683 AB - <p>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 <em>forgetting</em>, 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 <em>Forgetgol</em>, 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.</p> ER -