On the Design of PSyKI: A Platform for Symbolic Knowledge Injection into Sub-symbolic Predictors | SpringerLink
Skip to main content
Springer Nature Link
Log in

On the Design of PSyKI: A Platform for Symbolic Knowledge Injection into Sub-symbolic Predictors

  • Conference paper
  • First Online:
Explainable and Transparent AI and Multi-Agent Systems (EXTRAAMAS 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13283))

Abstract

A long-standing ambition in artificial intelligence is to integrate predictors’ inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from symbolic knowledge). Many methods in the literature support injection of symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, a unified, coherent software framework supporting them as well as their interchange, comparison, and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present the design of PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms. In particular, we discuss the overall architecture, and the many components/functionalities of PSyKI, invidually—providing examples as well. We finally demonstrate the versatility of our approach by exemplifying two custom injection algorithms in a toy scenario: Poker Hands classification.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 5719
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 7149
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    We stick to the authors’ dataset split – which is unusual, as the test set is far greater than the training set – since we are interested in testing whether SKI actually deals with the shortage of training data.

References

  1. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/

  2. Ajtai, M., Gurevich, Y.: Datalog vs first-order logic. J. Comput. Syst. Sci. 49(3), 562–588 (1994). https://doi.org/10.1016/S0022-0000(05)80071-6

    Article  MathSciNet  MATH  Google Scholar 

  3. Bader, S., d’Avila Garcez, A.S., Hitzler, P.: Computing first-order logic programs by fibring artificial neural networks. In: Russell, I., Markov, Z. (eds.) Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, Clearwater Beach, Florida, USA, pp. 314–319. AAAI Press (2005). http://www.aaai.org/Library/FLAIRS/2005/flairs05-052.php

  4. Badreddine, S., d’Avila Garcez, A., Serafini, L., Spranger, M.: Logic tensor networks. Artif. Intell. 303, 103649 (2022). https://doi.org/10.1016/j.artint.2021.103649

  5. Ballard, D.H.: Parallel logical inference and energy minimization. In: Kehler, T. (ed.) Proceedings of the 5th National Conference on Artificial Intelligence. Philadelphia, PA, USA, 11–15 August 1986. Volume 1: Science. pp. 203–209. Morgan Kaufmann (1986). http://www.aaai.org/Library/AAAI/1986/aaai86-033.php

  6. Besold, T.R., et al.: Neural-symbolic learning and reasoning: a survey and interpretation. CoRR abs/1711.03902 (2017). http://arxiv.org/abs/1711.03902

  7. Calegari, R., Ciatto, G., Omicini, A.: On the integration of symbolic and sub-symbolic techniques for XAI: a survey. Intell. Artif. 14(1), 7–32 (2020). https://doi.org/10.3233/IA-190036

    Article  Google Scholar 

  8. Cattral, R., Oppacher, F.: Poker hand data set, UCI machine learning repository (2007). https://archive.ics.uci.edu/ml/datasets/Poker+Hand

  9. Chang, M., Ratinov, L., Roth, D.: Guiding semi-supervision with constraint-driven learning. In: Carroll, J.A., van den Bosch, A., Zaenen, A. (eds.) ACL 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, 23–30 June 2007, Prague, Czech Republic. The Association for Computational Linguistics (2007). https://aclanthology.org/P07-1036/

  10. Demeester, T., Rocktäschel, T., Riedel, S.: Lifted rule injection for relation embeddings. In: Su, J., Carreras, X., Duh, K. (eds.) Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, Texas, USA, 1–4 November 2016, pp. 1389–1399. The Association for Computational Linguistics (2016). https://doi.org/10.18653/v1/d16-1146

  11. Diligenti, M., Gori, M., Saccà, C.: Semantic-based regularization for learning and inference. Artif. Intell. 244, 143–165 (2017). https://doi.org/10.1016/j.artint.2015.08.011

    Article  MathSciNet  MATH  Google Scholar 

  12. Diligenti, M., Roychowdhury, S., Gori, M.: Integrating prior knowledge into deep learning. In: Chen, X., Luo, B., Luo, F., Palade, V., Wani, M.A. (eds.) 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017, Cancun, Mexico, 18–21 December 2017, pp. 920–923. IEEE (2017). https://doi.org/10.1109/ICMLA.2017.00-37

  13. Evans, R., Grefenstette, E.: Learning explanatory rules from noisy data. J. Artif. Intell. Res. 61, 1–64 (2018). https://doi.org/10.1613/jair.5714

    Article  MathSciNet  MATH  Google Scholar 

  14. d’Avila Garcez, A.S., Gabbay, D.M.: Fibring neural networks. In: McGuinness, D.L., Ferguson, G. (eds.) Proceedings of the Nineteenth National Conference on Artificial Intelligence, Sixteenth Conference on Innovative Applications of Artificial Intelligence, 25–29 July 2004, San Jose, California, USA, pp. 342–347. AAAI Press/The MIT Press (2004). http://www.aaai.org/Library/AAAI/2004/aaai04-055.php

  15. d’Avila Garcez, A.S., Zaverucha, G.: The connectionist inductive learning and logic programming system. Appl. Intell. 11(1), 59–77 (1999). https://doi.org/10.1023/A:1008328630915

    Article  Google Scholar 

  16. Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 93:1–93:42 (2019). https://doi.org/10.1145/3236009

  17. Guo, S., Wang, Q., Wang, L., Wang, B., Guo, L.: Jointly embedding knowledge graphs and logical rules. In: Su, J., Carreras, X., Duh, K. (eds.) Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, Texas, USA, 1–4 November 2016, pp. 192–202. The Association for Computational Linguistics (2016). https://doi.org/10.18653/v1/d16-1019

  18. Harris, C.R., et al.: Array programming with NumPy. Nature 585(7825), 357–362 (2020). https://doi.org/10.1038/s41586-020-2649-2

    Article  Google Scholar 

  19. Hay, L.S.: Axiomatization of the infinite-valued predicate calculus. J. Symb. Log. 28(1), 77–86 (1963). http://www.jstor.org/stable/2271339

  20. Hu, Z., Ma, X., Liu, Z., Hovy, E.H., Xing, E.P.: Harnessing deep neural networks with logic rules. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, 7–12 August 2016, Berlin, Germany, Volume 1: Long Papers. The Association for Computer Linguistics (2016). https://doi.org/10.18653/v1/p16-1228

  21. Hu, Z., Yang, Z., Salakhutdinov, R., Xing, E.P.: Deep neural networks with massive learned knowledge. In: Su, J., Carreras, X., Duh, K. (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, 1–4 November 2016, pp. 1670–1679. The Association for Computational Linguistics (2016). https://doi.org/10.18653/v1/d16-1173

  22. Lipton, Z.C.: The mythos of model interpretability. Commun. ACM 61(10), 36–43 (2018). https://doi.org/10.1145/3233231

    Article  Google Scholar 

  23. Marra, G., Giannini, F., Diligenti, M., Gori, M.: LYRICS: a general interface layer to integrate logic inference and deep learning. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) ECML PKDD 2019, Part II. LNCS (LNAI), vol. 11907, pp. 283–298. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-46147-8_17

    Chapter  Google Scholar 

  24. McKinney, W.: Data structures for statistical computing in python. In: van der Walt, S., Millman, J. (eds.) Proceedings of the 9th Python in Science Conference, pp. 56–61 (2010). https://doi.org/10.25080/Majora-92bf1922-00a

  25. Parr, T.: The Definitive ANTLR 4 Reference. Pragmatic Bookshelf (2013)

    Google Scholar 

  26. Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

  27. Sabbatini, F., Ciatto, G., Calegari, R., Omicini, A.: On the design of PSyKE: a platform for symbolic knowledge extraction. In: Calegari, R., Ciatto, G., Denti, E., Omicini, A., Sartor, G. (eds.) Proceedings of the 22nd Workshop “From Objects to Agents”, Bologna, Italy, 1–3 September 2021. CEUR Workshop Proceedings, vol. 2963, pp. 29–48. CEUR-WS.org (2021). http://ceur-ws.org/Vol-2963/./paper14.pdf

  28. Sourek, G., Aschenbrenner, V., Zelezný, F., Schockaert, S., Kuzelka, O.: Lifted relational neural networks: efficient learning of latent relational structures. J. Artif. Intell. Res. 62, 69–100 (2018). https://doi.org/10.1613/jair.1.11203

    Article  MathSciNet  MATH  Google Scholar 

  29. Towell, G.G., Shavlik, J.W., Noordewier, M.O.: Refinement of approximate domain theories by knowledge-based neural networks. In: Shrobe, H.E., Dietterich, T.G., Swartout, W.R. (eds.) Proceedings of the 8th National Conference on Artificial Intelligence. Boston, Massachusetts, USA, 29 July–3 August 1990, 2 Volumes, pp. 861–866. AAAI Press/The MIT Press (1990). http://www.aaai.org/Library/AAAI/1990/aaai90-129.php

  30. Tresp, V., Hollatz, J., Ahmad, S.: Network structuring and training using rule-based knowledge. In: Hanson, S.J., Cowan, J.D., Giles, C.L. (eds.) Advances in Neural Information Processing Systems 5, [NIPS Conference, Denver, Colorado, USA, 30 November–3 December 1992], pp. 871–878. Morgan Kaufmann (1992). http://papers.nips.cc/paper/638-network-structuring-and-training-using-rule-based-knowledge

  31. Xie, Y., Xu, Z., Meel, K.S., Kankanhalli, M.S., Soh, H.: Embedding symbolic knowledge into deep networks. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8–14 December 2019, Vancouver, BC, Canada, pp. 4235–4245 (2019). https://proceedings.neurips.cc/paper/2019/hash/7b66b4fd401a271a1c7224027ce111bc-Abstract.html

  32. Xu, J., Zhang, Z., Friedman, T., Liang, Y., Van den Broeck, G.: A semantic loss function for deep learning with symbolic knowledge. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018. Proceedings of Machine Learning Research, vol. 80, pp. 5498–5507. PMLR (2018). http://proceedings.mlr.press/v80/xu18h.html

Download references

Acknowledgments

This paper is partially supported by the CHIST-ERA IV project CHIST-ERA-19-XAI-005, co-funded by EU and the Italian MUR (Ministry for University and Research).

Author information

Authors and Affiliations

  1. Dipartimento di Informatica – Scienza e Ingegneria (DISI), Alma Mater Studiorum—Università di Bologna, Cesena, Italy

    Matteo Magnini, Giovanni Ciatto & Andrea Omicini

Authors
  1. Matteo Magnini
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Giovanni Ciatto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrea Omicini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Matteo Magnini .

Editor information

Editors and Affiliations

  1. University of Applied Sciences and Arts of Western Switzerland, Sierre, Switzerland

    Davide Calvaresi

  2. Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg

    Amro Najjar

  3. Victoria University of Wellington, Wellington, New Zealand

    Michael Winikoff

  4. Umeå University, Umeå, Sweden

    Kary Främling

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Magnini, M., Ciatto, G., Omicini, A. (2022). On the Design of PSyKI: A Platform for Symbolic Knowledge Injection into Sub-symbolic Predictors. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds) Explainable and Transparent AI and Multi-Agent Systems. EXTRAAMAS 2022. Lecture Notes in Computer Science(), vol 13283. Springer, Cham. https://doi.org/10.1007/978-3-031-15565-9_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-15565-9_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-15564-2

  • Online ISBN: 978-3-031-15565-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation