Neuro-symbolic Weak Supervision: Theory and Semantics
This work addresses challenges in weakly supervised learning for real-world, high-stakes applications, though it appears incremental as it builds on existing neuro-symbolic and ILP methods.
The paper tackles the problem of interpretability and reliability in weak supervision, specifically in multi-instance partial label learning (MI-PLL), by proposing a neuro-symbolic framework that integrates Inductive Logic Programming to provide structured relational constraints, resulting in improved robustness, transparency, and accountability.
Weak supervision allows machine learning models to learn from limited or noisy labels, but it introduces challenges in interpretability and reliability - particularly in multi-instance partial label learning (MI-PLL), where models must resolve both ambiguous labels and uncertain instance-label mappings. We propose a semantics for neuro-symbolic framework that integrates Inductive Logic Programming (ILP) to improve MI-PLL by providing structured relational constraints that guide learning. Within our semantic characterization, ILP defines a logical hypothesis space for label transitions, clarifies classifier semantics, and establishes interpretable performance standards. This hybrid approach improves robustness, transparency, and accountability in weakly supervised settings, ensuring neural predictions align with domain knowledge. By embedding weak supervision into a logical framework, we enhance both interpretability and learning, making weak supervision more suitable for real-world, high-stakes applications.