用类人反思机制提升神经符号系统推理一致性
Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection
- 基于反事实学习框架，训练时生成纠错向量
- 推理时自动检测并修正神经网络输出错误
- 效率远超以往方法，适合资源受限场景
神经符号（NeSy）AI可类比人类双系统认知：神经网络模拟直觉型系统1，符号推理模拟算法型系统2。然而，面对复杂学习任务时，NeSy系统常产生与领域知识矛盾的输出，且难以修正。受人类认知反思启发——快速发现直觉判断错误并调用系统2修正，本文提出基于反事实学习（ABL）框架的归纳反思（ABL-Refl）机制。ABL-Refl在训练阶段利用领域知识推断出一个反思向量，该向量可在推理阶段识别神经网络输出中的潜在错误，并触发反事实推理进行修正，生成符合知识的一致输出。相比以往的ABL实现，ABL-Refl具有更高的效率。实验表明，其性能超越当前最优的NeSy方法，在更少训练资源下实现高精度和强效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。