Learning Compositional Rules via Neural Program Synthesis
This addresses the challenge of compositional generalization in AI, which is crucial for tasks like language understanding, though it is incremental as it builds on existing neural program synthesis techniques.
The paper tackles the problem of neural networks failing to generalize compositionally by introducing a neuro-symbolic model that learns rule systems from few examples, outperforming neural meta-learning in domains like SCAN and number word translation.
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.