Xiao-Wen Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiao-Wen Yang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jie-Jing Shao
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
2 shared publications - Hao-Ran Hao
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
1 shared publication - Lan-Zhe Guo
Nanjing University
1 shared publication - Wenda Wei
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
1 shared publication - Yu-Feng Li
Institute of High Energy Physics
1 shared publication - Yu-Feng Li
Nanjing University
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2861-2872
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.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2861-2872
Open AccessMitigating 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.
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1221-1232
Abductive Learning for Neuro-Symbolic Grounded Imitation
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1221-1232
Open AccessAbductive Learning for Neuro-Symbolic Grounded Imitation