Knowledge-Infused Learning: A Sweet Spot in Neuro-Symbolic AI

Deep learning has revolutionized the artificial intelligence (AI) landscape by enhancing machine capabilities to understand data-dependant relationships. On other hand, knowledge may not directly correlate or depend on data but represents facts that are true. Combining with data-driven deep techniques improves upon what can be learned from alone, resulting in improved performance reduced training, user-level explainability, modeling uncertainty learning, achieving context-sensitivity, and better control over behavior of AI systems such as assure safety avoid toxic behavior. We refer approach combining various types explicit knowledge-infused (KiL). Knowledge infusion brings symbolic into AI, giving us a class neuro-symbolic methods. The work KiL already developed suite context-adaptive algorithms infuses methods ways, broadly categorized shallow infusion, semi-deep infusion. This special issue allows interdisciplinary researchers practitioners diverse fields natural language processing, recommender systems, computer vision contribute their research external expert-curated methodologies for consistency robustness outcomes.