Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection

TL;DR

This paper introduces Abductive Reflection (ABL-Refl), a novel method inspired by human cognition, to improve neuro-symbolic AI systems by efficiently detecting and correcting inconsistencies during training and inference.

Contribution

The paper proposes ABL-Refl, an efficient approach that uses domain knowledge to identify and rectify errors in neuro-symbolic reasoning, outperforming existing methods.

Findings

ABL-Refl achieves higher accuracy than state-of-the-art methods.

It requires fewer training resources.

It significantly improves efficiency in neuro-symbolic reasoning.

Abstract

Neuro-Symbolic (NeSy) AI could be regarded as an analogy to human dual-process cognition, modeling the intuitive System 1 with neural networks and the algorithmic System 2 with symbolic reasoning. However, for complex learning targets, NeSy systems often generate outputs inconsistent with domain knowledge and it is challenging to rectify them. Inspired by the human Cognitive Reflection, which promptly detects errors in our intuitive response and revises them by invoking the System 2 reasoning, we propose to improve NeSy systems by introducing Abductive Reflection (ABL-Refl) based on the Abductive Learning (ABL) framework. ABL-Refl leverages domain knowledge to abduce a reflection vector during training, which can then flag potential errors in the neural network outputs and invoke abduction to rectify them and generate consistent outputs during inference. ABL-Refl is highly efficient in contrast to previous ABL implementations. Experiments show that ABL-Refl outperforms state-of-the-art NeSy methods, achieving excellent accuracy with fewer training resources and enhanced efficiency.