Improving Neural-based Classification with Logical Background Knowledge
This work addresses the challenge of combining neural networks with symbolic reasoning for multi-label classification, offering a practical solution for researchers and practitioners in neurosymbolic AI, though it is incremental as it builds upon existing techniques.
The paper tackles the problem of improving neural-based classification by integrating logical background knowledge, proposing a new neurosymbolic technique called semantic conditioning at inference that constrains outputs during inference without affecting training, and demonstrates it builds more accurate systems with fewer resources while ensuring semantic consistency.
Neurosymbolic AI is a growing field of research aiming to combine neural networks learning capabilities with the reasoning abilities of symbolic systems. This hybridization can take many shapes. In this paper, we propose a new formalism for supervised multi-label classification with propositional background knowledge. We introduce a new neurosymbolic technique called semantic conditioning at inference, which only constrains the system during inference while leaving the training unaffected. We discuss its theoritical and practical advantages over two other popular neurosymbolic techniques: semantic conditioning and semantic regularization. We develop a new multi-scale methodology to evaluate how the benefits of a neurosymbolic technique evolve with the scale of the network. We then evaluate experimentally and compare the benefits of all three techniques across model scales on several datasets. Our results demonstrate that semantic conditioning at inference can be used to build more accurate neural-based systems with fewer resources while guaranteeing the semantic consistency of outputs.