Neurosymbolic Learning

Ask about this topic

Overview

Neurosymbolic learning studies how to combine neural networks, which learn from data, with symbolic structures such as rules, logic, programs, and plans. Common approaches include differentiable logic and fuzzy constraints, probabilistic reasoning and answer set programming, and systems that learn rules or action models from examples. These methods are used in settings such as visual reasoning, robotics, process monitoring, scientific discovery, and classification with limited data or domain knowledge. A central challenge is making reasoning scalable and faithful: constraints can improve consistency and interpretability, but may hurt predictive performance or permit shortcuts that satisfy the rules without learning the intended concepts.

Latest papers

CardsList

62 papers6 papers in the last four weeks, down 14% on the four weeks before. 0.0% of all new papers.

  1. Soft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning

    Oct 21, 2026Tengwei Song, Robert HoehndorfNeurosymbolic LearningWeakly Supervised Learning

    CEMSE, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

  2. Neurosymbolic Learning of Interpretable World Models

    Oct 14, 2026Riccardo Andreoni, Massimiliano Ronzani, Chiara Ghidini +2Temporal LogicWorld Model Learning

    Fondazione Bruno Kessler · Free University of Bozen-Bolzano · Vrije Universiteit Amsterdam

  3. DPNL: A DPLL-based Algorithm for Probabilistic Neurosymbolic Learning

    Oct 5, 2026Thomas Jean-Michel Valentin, Pierre Genev{è}s, Luisa Sophie Werner +3Probabilistic LogicNeurosymbolic Learning

    ENS Paris Saclay,TYREX · LIG,TYREX · TYREX +1

  4. Prototype-Rule Neurosymbolic Regularization for Rank-Constrained Tensor Neural Networks under Label Scarcity

    Sep 30, 2026Eftychios Protopapadakis, Konstantinos Makantasis, Konstantinos M. GiannoutakisTensor NetworksPrototype Learning

    Department of Applied Informatics, University of Macedonia, 156 Egnatia Street, 54636 Thessaloniki, Greece · Department of Artificial Intelligence, Faculty of Information & Communication Technology, University of Malta, Msida, Malta

  5. Candidate Retention for Abductive Learning

    Sep 30, 2026Hao-Yuan He, Yu Liu, Ming LiAbductive ReasoningPseudo-Labeling

    School of Artificial Intelligence, Nanjing University · National Key Laboratory for Novel Software Technology, Nanjing University

  6. HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification

    Sep 29, 2026Simon Flügel, Till MossakowskiMulti-Label ClassificationExplainable Artificial Intelligence

    Institute for Computer Science, University of Osnabrück, Neuer Graben 29, 49074 Osnabrück, Germany

  7. Neuro-symbolic AI for Industrial Configuration

    Sep 24, 2026Danilo Valerio, Philipp Kogler, Stefan Bischof +2ManufacturingNeuro-Symbolic Reasoning

    Siemens AG Österreich · Siemens AG

  8. Neurosymbolic Action Model Learning under Partial Observability

    Sep 22, 2026Adem Kikaj, Lennert De Smet, Giuseppe Marra +1Symbolic PlanningNeurosymbolic Learning

    KU Leuven, Belgium

  9. Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents

    Sep 13, 2026Norbert Oswald, Fabian Deuser, Thomas BräunlNeuro-Symbolic RLReinforcement Learning

    Institute of Distributed Intelligent Systems University of the Bundeswehr Munich Munich, Germany · School of Engineering The University of Western Australia Perth, Australia

  10. Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach

    Sep 10, 2026Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar +1Symbolic ReasoningNeurosymbolic Learning

    Simula Research Laboratory, Oslo, Norway · Microsoft, Norway · LISN, CNRS, Paris-Saclay University, France

  11. NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry

    Sep 5, 2026Yicheng Lin, Zhipeng Fei, Yuxiu Xu +3Optical FlowVisual Odometry

    Guangzhou Purpleriver Electronic Technology Co., Ltd, Guangzhou, China · State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China

  12. Neural Symbollic Regression Using Deep Learning and Sparse Modelling

    Sep 1, 2026Ravi Kumar U, Sumitra SScientific MLNeurosymbolic Learning

    Department of Mathematics Indian Institute of Space Science and Technology Thiruvananthapuram, India

  13. Reinforcement Learning for Symbolic Equation Solving

    Aug 31, 2026Kevin P O KeeffeReinforcement LearningNeurosymbolic Learning

    Starling Research Institute

  14. Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation in the Brain

    Aug 29, 2026Teun van Gils, Rowan P. Sommers, Markus Ostarek +1Computational Cognitive ModelingNeurosymbolic Learning

    Neurobiology of Language Department, Max Planck Institute for Psycholinguistics · Donders Institute for Brain, Cognition and Behaviour, Radboud University

  15. NeSAM: Neuro-Symbolic Kinodynamics with Soil Adaptation for Off-Road Mobility

    Aug 21, 2026Chenhui Pan, Tong Xu, Francesco Cancelliere +1Terrain-Aware Robot LocomotionRobot Dynamics Learning

    Department of Computer Science, George Mason University, USA · Department of Electrical, Electronic and Computer Engineering, University of Catania, Italy

  16. Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits

    Aug 18, 2026Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho +1Neurosymbolic LearningLogical Reasoning

    Computer Science Program, Computer, Electrical, and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia

  17. Time to Reason: Scalable Neurosymbolic Learning for LTLf via Fuzzy Semantics

    Aug 17, 2026Riccardo Andreoni, Andrei Buliga, Alessandro Daniele +4Differentiable LogicNeuro-Symbolic Reasoning

    Fondazione Bruno Kessler, Via Sommarive, 18, Trento, 38123, Italy · Free University of Bozen-Bolzano, Via Bruno Buozzi, 1, Bolzano, 39100, Italy · Università di Bologna, Via Mura Anteo Zamboni 7, Bologna, 40126, Italy

  18. Learning to Assemble Novel Structures with Unfamiliar Parts under Semantic Constraints

    Aug 13, 2026Jonghyuk Park, Alex Lascarides, Subramanian RamamoorthyRobot LearningRobotic Assembly

    School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB, UK

  19. Moose: Latent concept learning with reasoning-shortcut awareness in EL++\mathcal{EL}^{++}

    Aug 13, 2026Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho +1Neurosymbolic LearningDescription Logic

    Computer Science Program, Computer, Electrical, and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia

  20. The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning

    Aug 4, 2026Agnese Chiatti, Michael Cochez, Cristina Cornelio +14Symbolic ReasoningNeuro-Symbolic Reasoning

    Politecnico di Milano · ELLIS Institute Finland & Abo Akademi University · Samsung AI +12

  21. SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

    Aug 4, 2026Yongchao HuangLatent Dynamics ModelingJoint-Embedding Predictive Architecture

  22. NSMA: Neuro-Symbolic Manifold Alignment for Generalizable Adaptive Bitrate Streaming under Texture Shift

    Jul 21, 2026Zhiqiang He, Zhi LiuNeural Network GeneralizationDomain Generalization

    The University of Electro-Communications Tokyo, Japan

  23. Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models

    Jul 9, 2026Jakob Suchan, Julius Monsen, Salim Baloch +1Energy-Based ModelsAnswer Set Programming

    Constructor University Bremen, Bremen, Germany · CoDesign Lab > Cognitive Vision · Örebro University, Örebro, Sweden

  24. Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning

    Jul 3, 2026Lucas ShenemanAutomatic DifferentiationDifferentiable Programming

    Institute for Interdisciplinary Data Sciences University of Idaho

  25. KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction

    Jun 24, 2026Naman Garg, Sarika Jain, Sourav Yadav +4GenomicsNeurosymbolic Learning

    National Institute of Technology Kurukshetra, Kurukshetra, India · Indian Institute of Information Technology Manipur, Manipur, India · Purdue University, West Lafayette, IN, USA +1

  26. NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning

    Jun 17, 2026Daniel Romero Schellhorn, Till Mossakowski, Björn GehrkeNeuro-Symbolic ReasoningNeurosymbolic Learning

    University of Osnabrück, Osnabrück, Germany

  27. EM-NeSy: Expectation Maximization for Neurosymbolic Learning

    Jun 12, 2026Annegret Seibt, Luc De Raedt, Giuseppe MarraSymbolic ReasoningExpectation-Maximization

    Department of Computer Science KU Leuven

  28. Accelerating NeurASP with vectorization and caching

    Jun 9, 2026Alexander Philipp Rader, Alessandra RussoAnswer Set ProgrammingNeuro-Symbolic Reasoning

    Imperial College London

  29. Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints

    Jun 5, 2026Qiwei Du, Zitong Zhan, Shaoshu Su +7Symbolic PlanningNeuro-Symbolic Planning

    Spatial AI & Robotics (SAIR) Lab, University at Buffalo, NY 14260 · Robotics Institute, Carnegie Mellon University, PA 15213

  30. DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

    May 28, 2026Shraman Pal, Can LiConvex RelaxationDifferentiable Optimization

    Davidson School of Chemical Engineering, Purdue University, West Lafayette, USA.