6 papers
Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems
Akihiro Takemura, Katsumi Inoue
Neurosymbolic (NeSy) systems integrate neural networks with logical reasoning to achieve both generalization and interpretability, but recent work has shown they are susceptible to…
Neural Decision-Propagation for Answer Set Programming
Thomas Eiter, Katsumi Inoue, Sota Moriyama
Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend the capabilities of ASP to r…
Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning
Akihiro Takemura, Katsumi Inoue, Masaaki Nishino
Neurosymbolic systems can satisfy logical constraints during learning without achieving the intended concept-label correspondence; this is a problem known as reasoning shortcuts. W…
Visual Perceptual to Conceptual First-Order Rule Learning Networks
Kun Gao, Davide SoldÃ, Thomas Eiter +1
Learning rules plays a crucial role in deep learning, particularly in explainable artificial intelligence and enhancing the reasoning capabilities of large language models. While e…
Formally Explaining Decision Tree Models with Answer Set Programming
Akihiro Takemura, Masayuki Otani, Katsumi Inoue
Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their com…
Generating Global and Local Explanations for Tree-Ensemble Learning Methods by Answer Set Programming
Akihiro Takemura, Katsumi Inoue
We propose a method for generating rule sets as global and local explanations for tree-ensemble learning methods using Answer Set Programming (ASP). To this end, we adopt a decompo…