【摘要】 因果关系的研究一直紧密围绕人类探索世界和发现世界的主题,传统的仅仅研究事物之间的统计相关关系作用有限,很难满足经济社会快速发展的需要.文章将自监督学习和对抗学习结合,利用图网络模型和系统动力学的反演模型,从大规模无监督数据中挖掘潜在的隐含信息,基于对比约束,构建物理驱动与数据驱动的统一框架,然后采用极大极小博弈策略学习不同因果模态的一致性表征,从而逼近真正的因果关系,为揭示潜藏在数据背后的内在规律提供了有力的分析工具.文章将非随机因果学习思想融入机器学习框架,对克服现有深度学习在抽象、推理及神经网络可解释性等方面的不足具有重要指导意义.更多还原

【Abstract】 The study of causality has always been the theme of human exploration of the world.The traditional study of only the correlation between things can no longer meet the needs of current economic and social development.This paper combines self-supervised learning and adversarial learning,and uses Bayesian network model and system dynamics inversion model to mine its own supervised information from large-scale unsupervised data.Based on comparative constraints,we build a unified framework of physical drive and data drive,and then use minimax game strategies to learn consistent representations of different causal modes.Therefore,the true causality can be approximated.It provides a powerful analysis tool for revealing the inherent laws hidden behind the data.This paper integrates the idea of non-random causal learning into the machine learning framework,which has important guiding significance for overcoming the shortcomings of existing deep learning in abstraction,reasoning and neural network interpretability.更多还原