Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems. However, some differentiable operators could bring a significant bias during backpropagation and degrade the performance of Neuro-Symbolic learning. In this paper, we reveal that this bias, named \textit{Implication Bias} is common in loss functions derived from fuzzy logic operators. Furthermore, we propose a simple yet effective method to transform the biased loss functions into \textit{Reduced Implication-bias Logic Loss (RILL)} to address the above problem. Empirical study shows that RILL can achieve significant improvements compared with the biased logic loss functions, especially when the knowledge base is incomplete, and keeps more robust than the compared methods when labelled data is insufficient.
翻译:将逻辑推理和机器学习结合起来,与不同操作者相近地进行逻辑推论,是神经-共振系统中广泛使用的一种技术。 但是,一些不同的操作者在后向反向调整过程中可能会带来重大偏差,并降低神经-共振学习的绩效。 在本文中,我们揭示出,这个称为\textit{impact Biaas}的偏差在来自模糊逻辑操作者的损失功能中很常见。此外,我们提出了一个简单而有效的方法,将偏向损失函数转换为\ textit{ reduced Indiction-biales(RIL)} 来解决上述问题。 经验学研究表明,与偏向逻辑损失功能相比,RILL可以取得显著的改进,特别是在知识基础不完整的情况下,并且比在标签数据不足时的比较方法更坚固。