Abstract
In this chapter, we describe how a logic program can be learned from data in a neuro symbolic framework. Our focus is on the gradient-based method known as differentiable inductive logic programming (ILP), which combines concepts from ILP with a neural architecture to support gradient-based learning. Additionally, we also cover several other paradigms to learn logical structures in a neuro symbolic framework.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Invented predicates are often referred to as auxiliary predicates.
- 2.
Note that in our complexity analysis (Sect. 8.3.3) we generalize this concept further where \(\mathit {int}_i\) is the number of intensional predicates permitted in the body.
- 3.
Note that we have omitted the conditional from the language in this chapter, and instead treat it as a defining characteristic of the environment.
- 4.
However, it is noted that consistency is not guaranteed and, as in [10], is addressed by adding a term to the loss function aiming to reduce the amount of inconsistency.
References
Aditya, D., Mukherji, K., Balasubramanian, S., Chaudhary, A., Shakarian, P.: PyReason: software for open world temporal logic. In: AAAI Spring Symposium (2023)
Badreddine, S., d’Avila Garcez, A., Serafini, L., Spranger, M.: Logic tensor networks. Artif. Intell. 303, 103649 (2022)
Chikara, N., Koshimura, M., Fujita, H., Hasegawa, R.: Inductive logic programming using a maxsat solver. In: 25th International Conference on Inductive Logic Programming (ILP 2015) (2015)
Cropper, A., Dumančić, S., Evans, R., Muggleton, S.H.: Inductive logic programming at 30. Mach. Learn. 111(1), 147–172 (2022)
Evans, R., Grefenstette, E.: Learning explanatory rules from noisy data. J. Artif. Int. Res. 61(1), 1–64 (2018)
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems, pp. 4107–4115 (2016)
Kifer, M., Subrahmanian, V.: Theory of generalized annotated logic programming and its applications. J. Log. Program. 12(3&4), 335–367 (1992)
Krishnan, G.P., Maier, F., Ramyaa, R.: Learning rules with stratified negation in differentiable ILP. In: Advances in Programming Languages and Neurosymbolic Systems Workshop (2021)
Muggleton, S.: Inverse entailment and progol. N. Gener. Comput. (Special issue on Inductive Logic Programming) 13(3–4), 245–286 (1995)
Riegel, R., Gray, A., Luus, F., Khan, N., Makondo, N., Akhalwaya, I.Y., Qian, H., Fagin, R., Barahona, F., Sharma, U., Ikbal, S., Karanam, H., Neelam, S., Likhyani, A., Srivastava, S.: Logical neural networks (2020). https://doi.org/10.48550/ARXIV.2006.13155. https://arxiv.org/abs/2006.13155
Sen, P., Carvalho, B.W.S.R.d., Riegel, R., Gray, A.: Neuro-symbolic inductive logic programming with logical neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36(8), pp. 8212–8219 (2022)
Shakarian, P., Simari, G.: Extensions to generalized annotated logic and an equivalent neural architecture. In: IEEE TransAI. IEEE (2022)
Shakarian, P., Simari, G.I., Callahan, D.: Reasoning about complex networks: a logic programming approach. Theory Pract. Log. Program. 13(4–5(Online-Supplement)) (2013)
Shakarian, P., Simari, G.I., Schroeder, R.: MANCaLog: a logic for multi-attribute network cascades. In: Gini, M.L., Shehory, O., Ito, T., Jonker, C.M. (eds.) International Conference on Autonomous Agents and Multi-Agent Systems AAMAS, pp. 1175–1176. IFAAMAS (2013)
Shindo, H., Nishino, M., Yamamoto, A.: Differentiable inductive logic programming for structured examples. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, pp. 5034–5041. AAAI Press (2021)
van Krieken, E., Acar, E., van Harmelen, F.: Analyzing differentiable fuzzy logic operators. Artif. Intell. 302, 103602 (2022)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Shakarian, P., Baral, C., Simari, G.I., Xi, B., Pokala, L. (2023). Neuro Symbolic Learning with Differentiable Inductive Logic Programming. In: Neuro Symbolic Reasoning and Learning. SpringerBriefs in Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-031-39179-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-39179-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39178-1
Online ISBN: 978-3-031-39179-8
eBook Packages: Computer ScienceComputer Science (R0)