Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
Gemini 2.5 Pro
GPT-5
GPT-4o
DeepSeek R1 via Azure
2000 character limit reached

A Survey on Neural-symbolic Learning Systems (2111.08164v3)

Published 10 Nov 2021 in cs.LG

Abstract: In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems exhibit exceptional cognitive intelligence but suffer from poor learning capabilities when compared to neural systems. Recognizing the advantages and disadvantages of both methodologies, an ideal solution emerges: combining neural systems and symbolic systems to create neural-symbolic learning systems that possess powerful perception and cognition. The purpose of this paper is to survey the advancements in neural-symbolic learning systems from four distinct perspectives: challenges, methods, applications, and future directions. By doing so, this research aims to propel this emerging field forward, offering researchers a comprehensive and holistic overview. This overview will not only highlight the current state-of-the-art but also identify promising avenues for future research.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (153)
  1. Learning to reason: Leveraging neural networks for approximate dnf counting, in: AAAI, pp. 3097–3104.
  2. Abductive Reasoning: Logical Investigations into Discovery and Explanation.
  3. Zero-shot multi-domain dialog state tracking using descriptive rules, in: IJCLR.
  4. Neural module networks, in: CVPR, pp. 39–48.
  5. Survey and critique of techniques for extracting rules from trained artificial neural networks, in: KBS, pp. 373–389.
  6. Hinge-loss markov random fields and probabilistic soft logic, in: arXiv preprint arXiv:1505.04406.
  7. Recent advances in hierarchical reinforcement learning, in: DEDS, pp. 41–77.
  8. Neural-symbolic learning and reasoning: A survey and interpretation, in: arXiv preprint arXiv:1711.03902.
  9. Translating embeddings for modeling multi-relational data, in: NIPS.
  10. Comet: Commonsense transformers for automatic knowledge graph construction, in: ACL.
  11. Abductive learning with ground knowledge base, in: IJCAI.
  12. On the integration of symbolic and sub-symbolic techniques for xai: A survey, in: IA, pp. 7–32.
  13. Logical rule induction and theory learning using neural theorem proving, in: NIPS.
  14. Knowledge graph transfer network for few-shot recognition, in: AAAI, pp. 10575–10582.
  15. Neural task planning with and–or graph representations, in: IEEE Transactions on Multimedia, pp. 1022–1034.
  16. Robot action planning by commonsense knowledge in human-robot collaborative tasks, in: IEMTRONICS, pp. 1–7.
  17. On the tractable counting of theory models and its application to truth maintenance and belief revision, in: JANCL, pp. 11–34.
  18. Sdd: A new canonical representation of propositional knowledge bases, in: AI.
  19. A knowledge compilation map, in: JAIR, pp. 229–264.
  20. Go for a walk and arrive at the answer: Reasoning over knowledge bases with reinforcement learning., in: NIPS.
  21. Chains of reasoning over entities, relations, and text using recurrent neural networks, in: ACL.
  22. Logical formalizations of commonsense reasoning: a survey, in: JAIR, pp. 651–723.
  23. Problog: A probabilistic prolog and its application in link discovery., in: IJCAI, pp. 2462–2467.
  24. Convolutional 2d knowledge graph embeddings, in: AAAI.
  25. Semantic-based regularization for learning and inference, in: AI, pp. 143–165.
  26. Mask r-cnn, in: ICCV, pp. 2961–2969.
  27. Unifying logical and statistical ai with markov logic, in: Commun.ACM, pp. 74–83.
  28. Logic tensor networks for semantic image interpretation, in: IJCAI.
  29. Neural logic machines, in: ICLR.
  30. Transforming probabilistic programs into algebraic circuits for inference and learning, in: NIPS.
  31. Neuro-symbolic constraint programming for structured prediction, in: arXiv preprint arXiv:2103.17232.
  32. Parameter estimation for probabilistic finite-state transducers, in: ACL, pp. 1–8.
  33. Library learning for neurally-guided bayesian program induction, in: NIPS.
  34. A mathematical introduction to logic.
  35. Learning explanatory rules from noisy data, in: JAIR, pp. 1–64.
  36. Coastal image interpretation using background knowledge and semantics, in: Comput Geosci, pp. 88–96.
  37. Fast rule mining in ontological knowledge bases with amie + +, in: VLDB, pp. 707–730.
  38. Neural-symbolic learning and reasoning: contributions and challenges, in: AAAI.
  39. Towards symbolic reinforcement learning with common sense, in: arXiv preprint arXiv:1804.08597.
  40. Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning, in: arXiv preprint arXiv:1905.06088.
  41. Neurosymbolic ai: the 3rd wave, in: arXiv preprint arXiv:2012.05876.
  42. The connectionist inductive learning and logic programming system, in: APIN, pp. 59–77.
  43. Neural-symbolic learning systems: foundations and applications.
  44. Efficient and expressive knowledge base completion using subgraph feature extraction, in: EMNLP, pp. 1488–1498.
  45. Towards deep symbolic reinforcement learning, in: NIPS.
  46. Neural module networks for reasoning over text, in: ICLR.
  47. Vquad: Video question answering diagnostic dataset, in: WACVW, pp. 282–291.
  48. A survey on cnn and rnn implementations, in: PESARO.
  49. Symbolic artificial intelligence and numeric artificial neural networks: towards a resolution of the dichotomy. Computational architectures integrating neural and symbolic processes: a perspective on the state of the art , 351–388.
  50. Harnessing deep neural networks with logic rules, in: ACL.
  51. Compositional attention networks for machine reasoning, in: ICLR.
  52. Learning by abstraction: The neural state machine, in: NIPS.
  53. A dual-system method for intelligent fault localization in communication networks, in: ICC 2022-IEEE International Conference on Communications, pp. 4062–4067.
  54. Adaptive convolution for multi-relational learning, in: NAACL HLT, pp. 978–987.
  55. Thinking, fast and slow.
  56. Neural-guided deductive search for real-time program synthesis from examples, in: ICLR.
  57. Rethinking knowledge graph propagation for zero-shot learning, in: CVPR, pp. 11487–11496.
  58. Mrkl systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning, in: arXiv preprint arXiv:2205.00445.
  59. Relational restricted boltzmann machines: A probabilistic logic learning approach, in: IJCLR, pp. 94–111.
  60. The third ai summer: Aaai robert s. engelmore memorial lecture. AI Magazine 43, 105–125.
  61. Learning markov logic networks via functional gradient boosting, in: ICDMW, pp. 320–329.
  62. Semi-supervised classification with graph convolutional networks, in: ICLR.
  63. Introduction to statistical relational learning.
  64. Graph neural networks meet neural-symbolic computing: A survey and perspective, in: AAAI.
  65. Discovering symbolic policies with deep reinforcement learning, in: ICML, pp. 5979–5989.
  66. Inductive logic programming., in: WLP, pp. 146–160.
  67. Gradient-based learning applied to document recognition, in: Proceedings of the IEEE, pp. 2278–2324.
  68. Standing on the shoulders of giant frozen language models, in: arXiv preprint arXiv:2204.10019.
  69. Large-scale few-shot learning: Knowledge transfer with class hierarchy, in: CVPR, pp. 7212–7220.
  70. Gated graph sequence neural networks, in: ICLR.
  71. Neural symbolic machines: Learning semantic parsers on freebase with weak supervision, in: ACL.
  72. Learning entity and relation embeddings for knowledge graph completion, in: AAAI.
  73. Od-gcn object detection by knowledge graph with gcn, in: arXiv preprint arXiv:1908.04385.
  74. Knowledge graph construction techniques, in: computer research and development, p. 582.
  75. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction, in: EMNLP.
  76. Context-aware zero-shot recognition, in: AAAI, pp. 11709–11716.
  77. Sdrl: interpretable and data-efficient deep reinforcement learning leveraging symbolic planning, in: AAAI, pp. 2970–2977.
  78. Deepproblog: Integrating logic and learning through algebraic model counting, in: NIPS.
  79. Deepproblog: Neural probabilistic logic programming, in: NeurIPS.
  80. The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision, in: arXiv preprint arXiv:1904.12584.
  81. The next decade in ai: four steps towards robust artificial intelligence. arXiv preprint arXiv:2002.06177 .
  82. Relational neural machines.
  83. From statistical relational to neural symbolic artificial intelligence: a survey, in: IJCAI.
  84. Integrating learning and reasoning with deep logic models, in: ECML PKDD.
  85. Neural markov logic networks, in: UAI.
  86. Semantic hierarchies for visual object recognition, in: CVPR, pp. 1–7.
  87. Openie-based approach for knowledge graph construction from text, in: Expert Syst. Appl., pp. 339–355.
  88. Reinforced anytime bottom up rule learning for knowledge graph completion, in: arXiv preprint arXiv:2004.04412.
  89. Bottom-up learning of markov logic network structure, in: ICML, pp. 625–632.
  90. Adversarial sets for regularising neural link predictors, in: arXiv preprint arXiv:1707.07596.
  91. Compositional vector space models for knowledge base inference, in: AAAI.
  92. Extracting meaningful high-fidelity knowledge from convolutional neural networks, in: IJCNN, pp. 1–17.
  93. Mathematical principles of fuzzy logic. volume 517.
  94. Learning to infer program sketches, in: ICML, pp. 4861–4870.
  95. Pr2 looking at things—ensemble learning for unstructured information processing with markov logic networks, in: ICRA, pp. 3916–3923.
  96. Generalizable neuro-symbolic systems for commonsense question answering, in: Neuro-Symbolic Artificial Intelligence: The State of the Art, pp. 294–310.
  97. Inductive logic programming via differentiable deep neural logic networks, in: arXiv preprint arXiv:1906.03523.
  98. Learning and reasoning about norms using neural-symbolic systems, in: AAMAS, pp. 1023–1030.
  99. Sound and efficient inference with probabilistic and deterministic dependencies, in: AAAI, pp. 458–463.
  100. Unsupervised semantic parsing, in: EMNLP, pp. 1–10.
  101. Learning to solve np-complete problems: A graph neural network for decision tsp, in: AAAI, pp. 4731–4738.
  102. Probabilistic logic neural networks for reasoning, in: ICLR.
  103. Survey on recommender systems incorporating trust, in: ICAAIC, pp. 1011–1015.
  104. Explainable machine learning practices: opening another black box for reliable medical ai, in: AI and Ethics, pp. 1–14.
  105. Markov logic networks, in: ML, pp. 107–136.
  106. Logical neural networks, in: arXiv preprint arXiv:2006.13155.
  107. Hyperspectral image classification using random forest and deep learning algorithms, in: LAGIRS, pp. 132–132.
  108. End-to-end differentiable proving, in: NIPS.
  109. A survey of decision tree classifier methodology, in: IEEE T SYST MAN CY-S, pp. 660–674.
  110. Transparency of deep neural networks for medical image analysis: A review of interpretability methods, in: CIBM, pp. 105–111.
  111. Modeling relational data with graph convolutional networks, in: ESWC, pp. 593–607.
  112. Logic tensor networks: Deep learning and logical reasoning from data and knowledge, in: arXiv preprint arXiv:1606.04422.
  113. Zero-shot learning with knowledge enhanced visual semantic embeddings, in: arXiv preprint arXiv:2011.10889.
  114. Encoding human domain knowledge to warm start reinforcement learning, in: AAAI, pp. 5042–5050.
  115. Discriminative training of markov logic networks, in: AAAI, pp. 868–873.
  116. Memory-efficient inference in relational domains, in: AAAI, pp. 488–493.
  117. Lifted relational neural networks: Efficient learning of latent relational structures, in: JAIR, pp. 69–100.
  118. Connectionist-symbolic integration: From unified to hybrid approaches.
  119. Computational architectures integrating neural and symbolic processes: A perspective on the state of the art .
  120. Neural semantic parsing in low-resource settings with back-translation and meta-learning, in: AAAI, pp. 8960–8967.
  121. Rotate: Knowledge graph embedding by relational rotation in complex space, in: ICLR.
  122. Commonsense knowledge in machine intelligence, in: SIGMOD, pp. 49–52.
  123. Inductive relation prediction by subgraph reasoning, in: ICML, pp. 9448–9457.
  124. Weakly supervised neural symbolic learning for cognitive tasks, in: AAAI.
  125. Knowledge-based artificial neural networks, in: AI, pp. 119–165.
  126. Extracting relational explanations from deep neural networks: A survey from a neural-symbolic perspective, in: TNNLS, pp. 3456–3470.
  127. Event modeling and recognition using markov logic networks, in: ECCV, pp. 610–623.
  128. Complex embeddings for simple link prediction, in: ICML, pp. 2071–2080.
  129. Composition-based multi-relational graph convolutional networks, in: ICLR.
  130. Informed machine learning–a taxonomy and survey of integrating prior knowledge into learning systems, in: TKDE, pp. 614–633.
  131. Logic rules powered knowledge graph embedding, in: arXiv preprint arXiv:1903.03772.
  132. Zero-shot recognition via semantic embeddings and knowledge graphs, in: CVPR, pp. 6857–6866.
  133. Generalizing from a few examples: A survey on few-shot learning, in: CSUR, pp. 1–34.
  134. Robust embedding with multi-level structures for link prediction., in: IJCAI, pp. 5240–5246.
  135. Knowledge graph embedding by translating on hyperplanes, in: AAAI.
  136. Deep learning-based perception systems for autonomous driving: A comprehensive survey, in: Neurocomputing.
  137. A comprehensive survey on graph neural networks, in: TNNLS, pp. 4–24.
  138. Embedding symbolic knowledge into deep networks .
  139. Deeppath: A reinforcement learning method for knowledge graph reasoning, in: EMNLP.
  140. A semantic loss function for deep learning with symbolic knowledge, in: ICML, pp. 5502–5511.
  141. Embedding entities and relations for learning and inference in knowledge bases, in: ICLR.
  142. Peorl: Integrating symbolic planning and hierarchical reinforcement learning for robust decision-making, in: IJCAI.
  143. Differentiable learning of logical rules for knowledge base completion, in: NIPS.
  144. Learn to explain efficiently via neural logic inductive learning, in: ICLR.
  145. Neural-symbolic vqa: Disentangling reasoning from vision and language understanding, in: NIPS.
  146. A probabilistic graphical model based on neural-symbolic reasoning for visual relationship detection, in: CVPR, pp. 10609–10618.
  147. Neural, symbolic and neural-symbolic reasoning on knowledge graphs, in: AI Open, pp. 14–35.
  148. Efficient probabilistic logic reasoning with graph neural networks, in: ICLR.
  149. A decadal survey of zero-shot image classification, in: SCIENTIA SINICA Informationis, pp. 1299–1320.
  150. Abductive learning: towards bridging machine learning and logical reasoning, in: Science China Information Sciences, pp. 1–3.
  151. Reasoning about object affordances in a knowledge base representation, in: ECCV, pp. 408–424.
  152. Faithfully explainable recommendation via neural logic reasoning, in: ACL.
  153. Symbolic learning and reasoning with noisy data for probabilistic anchoring, in: Front. Robot. AI, p. 100.
Citations (42)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now