Hybrid Neuro-Symbolic Reasoning Algorithms for Explainable Artificial Intelligence in Causal Representation Learning
Keywords:
Neuro-symbolic AI, Causal learning, Explainable AI, Causal graphs, Symbolic reasoning, Deep learning, Representation learning, Hybrid AI, Interpretable models, Structural causal modelsAbstract
In the quest for explainable artificial intelligence (XAI), combining the strengths of data-driven neural networks with symbolic reasoning offers a promising path toward interpretable and generalizable models. This paper proposes a hybrid neuro-symbolic reasoning framework that facilitates causal representation learning with human-interpretable reasoning mechanisms. By leveraging the learning capacity of deep neural networks and the structured logic of symbolic systems, the approach bridges the gap between raw data representation and causal knowledge extraction. We demonstrate the framework’s effectiveness on benchmark datasets through experiments highlighting improved generalization and transparency in reasoning
References
Pearl, J. (2000). Causality: Models, Reasoning, and Inference. Cambridge University Press.
Kodi, D., & Chundru, S. (2025). Unlocking New Possibilities: How Advanced API Integration Enhances Green Innovation and Equity. In Advancing Social Equity Through Accessible Green Innovation (pp. 24). IGI Global. https://doi.org/10.4018/979-8-3693-9471-7.ch027
Peters, J., Janzing, D., & Schölkopf, B. (2017). Elements of Causal Inference. MIT Press.
Bengio, Y., et al. (2019). A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms. NeurIPS.
Marella, B.C.C., & Kodi, D. (2025). Generative AI for Fraud Prevention: A New Frontier in Productivity and Green Innovation. In Advancing Social Equity Through Accessible Green Innovation (pp. 1–16). IGI Global. https://doi.org/10.4018/979-8-3693-9471-7.ch012
Evans, R., & Grefenstette, E. (2018). Learning Explanatory Rules from Noisy Data. JAIR.
Mukesh, V., Joel, D., Balaji, V. M., Tamilpriyan, R., & Yogesh Pandian, S. (2024). Data management and creation of routes for automated vehicles in smart city. International Journal of Computer Engineering and Technology (IJCET), 15(36), 2119–2150. doi: https://doi.org/10.5281/zenodo.14993009
Yang, Y., et al. (2021). Neural Causal Models for Visual Inference. ICLR.
K. R. Kotte, L. Thammareddi, D. Kodi, V. R. Anumolu, A. K. K and S. Joshi, "Integration of Process Optimization and Automation: A Way to AI Powered Digital Transformation," 2025 First International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies (CE2CT), Bhimtal, Nainital, India, 2025, pp. 1133-1138, doi: 10.1109/CE2CT64011.2025.10939966.
Marcus, G. (2020). The Next Decade in AI: Why Common Sense is Needed. arXiv:2002.06177.
Kodi, D. (2024). Automating Software Engineering Workflows: Integrating Scripting and Coding in the Development Lifecycle . Journal of Computational Analysis and Applications (JoCAAA), 33(4), 635–652.
Chen, Z., et al. (2022). Logic-Guided Visual Reasoning with Causal Attention. CVPR.
Kodi, D. (2024). Data Transformation and Integration: Leveraging Talend for Enterprise Solutions. International Journal of Innovative Research in Science, Engineering and Technology, 13(9), 16876–16886. https://doi.org/10.15680/IJIRSET.2024.1309124
Lake, B. M., et al. (2017). Building Machines That Learn and Think Like People. BBS.
