IID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirements
This is an incremental position paper that outlines a research agenda for improving neurosymbolic AI by better integrating logical constraints, potentially benefiting researchers in AI and machine learning.
The paper addresses the challenge of relaxing the IID assumption in machine learning when incorporating neurosymbolic background knowledge, proposing a hierarchy of logics to fit different use case requirements and arguing that this expressivity impacts ML routine design.
Neurosymbolic background knowledge and the expressivity required of its logic can break Machine Learning assumptions about data Independence and Identical Distribution. In this position paper we propose to analyze IID relaxation in a hierarchy of logics that fit different use case requirements. We discuss the benefits of exploiting known data dependencies and distribution constraints for Neurosymbolic use cases and argue that the expressivity required for this knowledge has implications for the design of underlying ML routines. This opens a new research agenda with general questions about Neurosymbolic background knowledge and the expressivity required of its logic.