KG-DG: Knowledge-Guided Domain Generalization via Neuro-Symbolic Fusion

Midhat Urooj, Ayan Banerjee, Sandeep Gupta

Keywords: Neuro-Symbolic Learning

TL;DR: Single and Cross Domain Generalization in Medical Classification: A Neuro-Symbolic Learning Approach

Abstract: Abstract. Domain generalization remains a critical challenge in medical imaging, where models trained on single sources often fail under real-world distribution shifts. We propose KG-DG, a neuro-symbolic framework for diabetic retinopathy (DR) classification that integrates vision transformers with expert-guided symbolic reasoning to enable robust generalization across unseen domains. Our approach leverages clinical lesion ontologies through structured, rule-based features and retinal vessel segmentation, fusing them with deep visual representations via a confidence-weighted integration strategy. The framework addresses both single-domain generalization (SDG) and multi-domain generalization (MDG) by minimizing the KL divergence between domain embeddings, thereby enforcing alignment of high-level clinical semantics. Extensive experiments across four public datasets (APTOS, EyePACS, Messidor-1, Messidor-2) demonstrate significant improvements: up to a 5.2% accuracy gain in cross-domain settings and a 6% improvement over baseline ViT models. Notably, our symbolic-only model achieves a 63.67% average accuracy in MDG, while the complete neuro-symbolic integration achieves the highest accuracy compared to existing published baselines and benchmarks in challenging SDG scenarios. Ablation studies reveal that lesion-based features (84.65% accuracy) substantially outperform purely neural approaches, confirming that symbolic components act as effective regularizers beyond merely enhancing interpretability. Our findings establish neuro-symbolic integration as a promising paradigm for building clinically robust, and domain-invariant medical AI systems. Keywords: Domain Generalization, Neuro-Symbolic Learning, Medical Imaging, Diabetic Retinopathy, Vision Transformers, Out-of-Distribution Robustness

Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)

Submission Number: 24022