Knowledge Tree
Neuro-Symbolic Learning
Also known as: neuro-symbolic representation learning, Neural-Symbolic Learning Systems, neural-symbolic learning
Facts (18)
Sources
Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org Nov 7, 2024 12 facts
claimThe conversion of representations between neural networks and symbolic logic is a persistent challenge in neuro-symbolic learning.
referenceFadi Al Machot (2023) introduced ASPER, a neural-symbolic approach for enhanced reasoning in neural models, published as an arXiv preprint.
referenceXixi Zhu, Bin Liu, Cheng Zhu, Zhaoyun Ding, and Li Yao published the paper 'Approximate Reasoning for Large-Scale ABox in OWL DL Based on Neural-Symbolic Learning' in the journal Mathematics in 2023, which explores neural-symbolic learning methods for reasoning in Description Logic (OWL DL).
referenceHe et al. (2024) introduced a reduced implication-bias logic loss function designed for neuro-symbolic learning.
claimHe et al. (2024), Arrotta et al. (2023), Xu et al. (2018), and Arrotta et al. (2024) proposed loss functions suitable for Neuro-Symbolic Learning, while Ahmed et al. (2022b) proposed a regularization method suitable for neuro-symbolic learning.
referenceNuri Cingillioglu completed a Ph.D. dissertation at Imperial College London in 2022 focused on end-to-end neuro-symbolic learning of logic-based inference.
referenceDaniel Cunnington, Mark Law, Jorge Lobo, and Alessandra Russo developed a method for the neuro-symbolic learning of answer set programs from raw data, detailed in a 2022 arXiv preprint.
procedureThe authors of the survey paper searched Google Scholar and Research Gate for research on 'neuro-symbolic', 'neuro symbolic', and 'neuro symbolic learning' from 2014 to 2024 to analyze research trends.
referenceStehr et al. (2022) proposed a probabilistic approximate logic framework for neuro-symbolic learning and reasoning.
referenceYifeng Wang, Zhi Tu, Yiwen Xiang, Shiyuan Zhou, Xiyuan Chen, Bingxuan Li, and Tianyi Zhang developed a neuro-symbolic learning approach for rapid image labeling in 2023.
claimStudies by He et al. (2024), Arrotta et al. (2023), Xu et al. (2018), Arrotta et al. (2024), and Ahmed et al. (2022b) did not improve the interpretability of Neuro-Symbolic Learning models.
referenceAlshahrani et al. (2017) developed a neuro-symbolic representation learning method applied to biological knowledge graphs, published in the journal Bioinformatics.
Neuro-symbolic AI - Wikipedia en.wikipedia.org 1 fact
referenceArtur S. d'Avila Garcez, Krysia Broda, and Dov M. Gabbay authored the book 'Neural-Symbolic Learning Systems: Foundations and Applications', which details the theoretical and practical foundations of the field.
Papers - Dr Vaishak Belle vaishakbelle.github.io 1 fact
referenceVaishak Belle authored 'On the relevance of logic for AI, and the promise of neuro-symbolic learning', published in Neurosymbolic Artificial Intelligence in 2025.
A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Dec 9, 2025 1 fact
referenceYu, Yang, Liu, Wang, and Pan (2023) provide a survey of existing neural-symbolic learning systems.
The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org Jul 11, 2024 1 fact
referenceArtur d’Avila Garcez et al. discussed the contributions and challenges of neural-symbolic learning and reasoning.
Call for Papers: KR meets Machine Learning and Explanation kr.org 1 fact
claimThe KR 2026 special track 'KR meets Machine Learning and Explanation' invites research on the intersection of Knowledge Representation and Machine Learning, specifically covering topics such as learning symbolic knowledge (ontologies, knowledge graphs, action theories), KR-driven plan computation, logic-based learning, neural-symbolic learning, statistical relational learning, symbolic reinforcement learning, and the mutual use of KR techniques and LLMs.
Call for Papers: Special Session on KR and Machine Learning kr.org 1 fact
claimThe Special Session on KR and Machine Learning at KR2022 welcomes papers on topics including learning symbolic knowledge (ontologies, knowledge graphs, action theories, commonsense knowledge, spatial/temporal theories, preference/causal models), logic-based/relational learning algorithms, machine-learning driven reasoning, neural-symbolic learning, statistical relational learning, multi-agent learning, symbolic reinforcement learning, learning symbolic abstractions from unstructured data, explainable AI, expressive power of learning representations, knowledge-driven natural language understanding and dialogue, knowledge-driven decision making, knowledge-driven intelligent systems for IoT and cybersecurity, and architectures combining data-driven techniques with formal reasoning.