NeSy-Resource

Neural Symbolic Systems Resources

神经符号系统相关研究资源汇总

Note:

• ⭐ Please leave a STAR if you like this project! ⭐
• If you find any incorrect / inappropriate / outdated content, please kindly consider opening an issue or a PR.
• We would greatly appreciate your contribution to this list, and you will appear in the contributors✨!

About

This repository offers a curated collection of research and development resources in the field of neural symbolic system.

---

Table of Contents

• 1. Cornerstone
• 2. Books
• 3. Survey and Benchmark
  • 3.1. Survey
  • 3.2. Benchmark
• 4. Neural-symbolic Learning Systems
  • 4.1. Frameworks
• 5. Related Organization
• 6. Contributors

---

Cornerstone

• annotated logic
• fuzzy logic
• differentiable logic

Books

Neuro Symbolic Reasoning and Learning by Paulo Shakarian , Chitta Baral , Gerardo I. Simari , Bowen Xi , Lahari Pokala(Arizona State University)

Neuro Symbolic Learning Systems:Foundations and Applications by Artur S. d’Avila Garcez , Krysia B. Broda , Dov M. Gabbay(London)

Survey and Benchmark

Survey

• From statistical relational to neurosymbolic artificial intelligence: A survey. Giuseppe Marra. Artificial Intelligence, 2024
• A survey on neural-symbolic learning systems. Shirui Pan. Neural Networks, 2023.
• Neurosymbolic AI: the 3rd wave. Garcez. Artificial Intelligence Review, 2023.
• Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems. Laura von Rueden. IEEE Transactions on Knowledge and Data Engineering 2023
• The third AI summer: AAAI Robert S. Engelmore Memorial Lecture. Henry Kautz. AI Magazine, 2022.
• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence. Gary Marcus. eprint arXiv, 2020.
• Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective. Luis C. Lamb. eprint arXiv, 2020
• On the integration of symbolic and sub-symbolic techniques for XAI: A survey. Roberta Calegari. Intelligenza Artificiale 2020.
• Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective. Joseph Townsend. IEEE Transactions on Neural Networks and Learning Systems, 2020
• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation. Tarek R Besold. eprint arXiv, 2017.
• Neural-symbolic learning systems: foundations and applications. Garcez. Book, 2002&2012.
• Survey and critique of techniques for extracting rules from trained artificial neural networks. Alan B. Tickle. Knowledge-Based Systems 1995.

Benchmark

• Contemporary Symbolic Regression Methods and their Relative Performance. William La Cava. eprint arXiv, 2021.[evaluation]

Neural-symbolic Learning Systems

Frameworks

• LTNs(Logic Tensor Networks)
  • Paper:Logic Tensor Networks
  • Code(PyTorch)
  • Code(Tensorflow)
• RRNs(Recursive Reasoning Networks)
  • Paper:Ontology Reasoning with Deep Neural Networks
  • Code(DataGen1)
  • Code(DataGen2)
• LNNs(Logical Neural Networks)
  • Paper1:Logical Neural Network
  • Paper2:Foundations of Reasoning with Uncertainty via Real-valued Logics
  • Paper3:Training Logical Neural Networks by Primal–Dual Methods for Neuro-Symbolic Reasoning
  • Paper4:Proof Extraction for Logical Neural Networks
  • Code
  • Learning Materials
• NeurASP
  • Paper:NeurASP: Embracing Neural Networks into Answer Set Programming
  • Code
• ILP(Inductive Logic Programming)
  • Paper1:Learning Explanatory Rules from Noisy Data
  • Paper2:Inductive logic programming at 30: a new introduction
  • Paper3:αILP: thinking visual scenes as differentiable logic programs
  • Code
  • Learning Materials
• SATNet
  • Paper:SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver
  • Code
• DSO/DSP(Deep Symbolic Policy Learning)
  • Paper1:Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
  • Paper2:Discovering symbolic policies with deep reinforcement learning
  • Paper3:Symbolic Regression via Neural-Guided Genetic Programming Population Seeding
  • Paper4: A Unified Framework for Deep Symbolic Regression.
  • Paper5:Improving exploration in policy gradient search: Application to symbolic optimization.
  • Paper6:An interactive visualization platform for deep symbolic regression
  • Paper7:Incorporating domain knowledge into neural-guided search via in situ priors and constraints
  • Paper8:Distilling Wikipedia mathematical knowledge into neural network models
  • Paper9:Leveraging Language Models to Efficiently Learn Symbolic Optimization Solutions
  • Paper10:Deep Symbolic Optimization for Electric Component Sizing in Fixed Topology Power Converters
  • Paper11:DisCo-DSO: Coupling Discrete and Continuous Optimization for Efficient Generative Design in Hybrid SpacesBlogPost
  • Code
• STLNet
  • Paper:STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks
• ABL(Abductive Learning)
  • Paper:Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection
  • Code
  • Learning Materials
• (Deep)ProbLog
  • Paper1:ProbLog: a probabilistic prolog and its application in link discovery
  • Paper2:DeepProbLog: Neural Probabilistic Logic Programming
  • Paper3:Neural probabilistic logic programming in DeepProbLog
  • Code1
  • Code2
  • Learning Materails
• DeepStochLog(Neural Stochastic Logic Programming)
  • Paper:DeepStochLog: neural stochastic logic programming
  • Code
• Difflog
  • Paper:Synthesizing Datalog Programs Using Numerical Relaxation
  • Code
• DL2
  • Paper:DL2: Training and Querying Neural Networks with Logic
  • Code
• DLM
  • Paper:Integrating Learning and Reasoning with Deep Logic Models
  • Code

Related organization

Organization	Related Research	Status
IBM	LNN
Sony	LTN	🟢 Regularly
DARPA	ANSR	🟡 No updates
Meta	NeurIPS	🟢 Regularly
Oxford	ILP
Carnegie Mellon University	SATNet
LLNL(Lawrence Livermore National Laboratory)	DSO
Nanjing University	ABL	🟢 Regularly
KU Leuven Machine Learning Research Group	ProLog	🟢 Regularly

Contributors 🌟

Thanks goes to wonderful me!

Fulin Zhou 🎯 📝