State-of-the-art neurosymbolic learning systems use probabilistic reasoning to guide neural networks towards predictions that conform to logical constraints over symbols. Many such systems assume that the probabilities of the considered symbols are conditionally independent given the input to simplify learning and reasoning. We study and criticise this assumption, highlighting how it can hinder optimisation and prevent uncertainty quantification. We prove that loss functions bias conditionally independent neural networks to become overconfident in their predictions. As a result, they are unable to represent uncertainty over multiple valid options. Furthermore, we prove that these loss functions are difficult to optimise: they are non-convex, and their minima are usually highly disconnected. Our theoretical analysis gives the foundation for replacing the conditional independence assumption and designing more expressive neurosymbolic probabilistic models.
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
Golden Gate University, San Francisco Foundation(金门大学,旧金山基金会);AgenticOS (FAOS)(AgenticOS(FAOS));Associate Director, Data, Digital & IT Novartis Healthcare Pvt. Ltd.(数据、数字与IT部门,诺华健康有限公司);Novartis Healthcare Pvt. Ltd., Hyderabad, India(诺华健康有限公司,海得拉巴,印度)
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
Department of Computer Science, University of British Columbia, Vancouver, Canada(不列颠哥伦比亚大学计算机科学系,温哥华,加拿大);Alberta Machine Intelligence Institute, Edmonton, Canada(阿尔伯塔机器智能研究所,爱德蒙顿,加拿大)