Learning Compositional Rules via Neural Program Synthesis

TitleLearning Compositional Rules via Neural Program Synthesis
Publication TypeConference Paper
Year of Publication2020
AuthorsNye, M, Solar-Lezama, A, Tenenbaum, JB, Lake, BM
Conference NameAdvances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020)
Date Published12/2020
Abstract

Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and combining these rules to form compositional rule-based systems. Current neural architectures, on the other hand, often fail to generalize in a compositional manner, especially when evaluated in ways that vary systematically from training. In this work, we present a neuro-symbolic model which learns entire rule systems from a small set of examples. Instead of directly predicting outputs from inputs, we train our model to induce the explicit system of rules governing a set of previously seen examples, drawing upon techniques from the neural program synthesis literature. Our rule-synthesis approach outperforms neural meta-learning techniques in three domains: an artificial instruction-learning domain used to evaluate human learning, the SCAN challenge datasets, and learning rule-based translations of number words into integers for a wide range of human languages.

Code can be found at this https URL | arXive entry

URLhttps://proceedings.neurips.cc/paper/2020/hash/7a685d9edd95508471a9d3d6fcace432-Abstract.html
Download:  PDF icon 2003.05562.pdf

Associated Module: 

CBMM Relationship: 

  • CBMM Funded