A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification

TL;DR

This paper introduces a neurosymbolic framework combining epistemic deep learning and fuzzy logic to improve hierarchical image classification, ensuring more calibrated, consistent, and interpretable predictions.

Contribution

It is the first to unify neurosymbolic reasoning with epistemic modeling in hierarchical classification, enhancing uncertainty estimation and logical consistency.

Findings

Maintains accuracy comparable to transformer baselines.

Provides more calibrated and interpretable predictions.

Reduces overconfidence and enforces hierarchical consistency.

Abstract

Deep neural networks achieve high accuracy on image classification tasks. Yet, they often produce overconfident predictions as which fail to express epistemic uncertainty, and frequently violate logical or structural constraints present in the data. These limitations are particularly pronounced in hierarchical classification, where predictions across fine and coarse levels must remain coherent. We propose, for the first time, a unified neurosymbolic and epistemic modelling framework that augments Swin Transformers with focal set reasoning and differentiable fuzzy logic. Rather than treating labels as isolated categories, our method induces data-driven focal sets within the learnt embedding space, which helps capture epistemic uncertainty over multiple plausible fine-grained classes. These focal sets form the basis of a belief-theoretic layer that uses fuzzy membership functions and t-norm conjunctions to encourage consistency between fine- and coarse-grained predictions. A learnable loss further balances calibration, mass regularisation, and logical consistency, allowing the model to adaptively trade off symbolic structure with data-driven evidence. In experiments on hierarchical image classification, our framework maintains accuracy on par with transformer baselines while providing more calibrated and interpretable predictions, reducing overconfidence and enforcing high logical consistency across hierarchical outputs. Our experimental results show that combining focal set reasoning with fuzzy logic provides a practical step toward deep learning models that are both accurate and epistemically aware.