Mitigating Neuro-Symbolic Reasoning Shortcuts with Data-Driven Knowledge Augmentation

Recent advancements in neuro-symbolic learning (NeSy) have shown significant promise in integrating deep learning with symbolic reasoning, offering both interpretability and generalization. However, the prevalence of reasoning shortcuts, where the NeSy system predicts incorrect intermediate concepts while maintaining high final accuracy, poses a substantial challenge. This is especially problematic in domains requiring reliable and transparent decision-making. Inspired by recent theories, we find that existing methods fail to address the reasoning shortcut issue when the knowledge base lacks sufficient complexity, highlighting their vulnerability in real-world applications. In this work, we present a novel method called DKA to address this issue. It introduces a limited set of concept-supervised data to enhance the knowledge base, effectively solving the reasoning shortcut problem and improving the applicability of the NeSy system. Theoretical analysis reveals that DKA can reduce shortcut risks with improved data efficiency. Empirical studies across multiple tasks within various neuro-symbolic frameworks also verify the effectiveness of the DKA method.