摘要
近年来,许多研究工作致力于将数据驱动的机器学习和知识驱动的逻辑推理相结合,以提高机器学习的性能.其中,不少工作尝试利用反绎推理,将机器学习与逻辑推理融合到一个框架中.这些方法通过机器学习模型生成伪标记,然后利用反绎推理来修正不一致的伪标记,以更新机器学习模型并多次迭代.然而,反绎中可能会存在错误标记,这些标记会对模型训练产生负面影响且难以被发现.因此提出一种带拒绝推理的反绎学习方法,它同时考虑反绎标记的模型不确定性和推理不确定性,从数据层面和知识层面综合评估反绎结果的可靠性,并通过拒绝部分反绎推理结果来避免不可靠的反绎标记对模型训练的负面影响.实验表明,提出的方法可以减少错误反绎标记的比例、加速反绎学习的训练并带来更好的性能.
In recent years,many research efforts have focused on combining data-driven machine learning with knowledge-driven logical reasoning,aiming to improve the performance of machine learning systems.Many works have attempted to use abductive reasoning to integrate machine learning and logical reasoning into a unified framework.These methods typically first generate pseudo-labels through machine learning models,and then use abductive reasoning to revise the inconsistent pseudo-labels,which serves to update the machine learning model and the above routine repeats.However,there may be incorrect labels in the abduced labels,which could have a negative impact on the training of the machine learning model and are challenging to detect.We propose abductive learning with rejection reasoning,a method that takes into account both model uncertainty and reasoning uncertainty of the abduced labels.This strategy comprehensively evaluates the reliability of abductive results from the perspective of both the data and knowledge levels,and avoids the negative impact of unreliable abduced labels on model training by rejecting some of the abductive reasoning results.Empirical studies show that the proposed method can reduce the proportion of incorrect abduced labels.In turn,this facilitates a faster training process for abductive learning and improves its overall performance.
作者
黄宇轩
姜远
Huang Yuxuan;Jiang Yuan(National Key Laboratory for Novel Software Technology(Nanjing University),Nanjing 210023)
出处
《计算机研究与发展》
EI
CSCD
北大核心
2024年第7期1791-1798,共8页
Journal of Computer Research and Development
基金
国家自然科学基金项目(62176117)。
关键词
反绎学习
机器学习
逻辑推理
反绎推理
神经符号学习
abductive learning
machine learning
logical reasoning
abductive reasoning
neuro-symbolic learning
