A General-Purpose Protocol for Multi-agent Based Explanations | SpringerLink
Skip to main content
Springer Nature Link
Log in

A General-Purpose Protocol for Multi-agent Based Explanations

  • Conference paper
  • First Online:
Explainable and Transparent AI and Multi-Agent Systems (EXTRAAMAS 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14127))

  • 393 Accesses

Abstract

Building on prior works on explanation negotiation protocols, this paper proposes a general-purpose protocol for multi-agent systems where recommender agents may need to provide explanations for their recommendations. The protocol specifies the roles and responsibilities of the explainee and the explainer agent and the types of information that should be exchanged between them to ensure a clear and effective explanation. However, it does not prescribe any particular sort of recommendation or explanation, hence remaining agnostic w.r.t. such notions. Novelty lays in the extended support for both ordinary and contrastive explanations, as well as for the situation where no explanation is needed as none is requested by the explainee.

Accordingly, we formally present and analyse the protocol, motivating its design and discussing its generality. We also discuss the reification of the protocol into a re-usable software library, namely PyXMas, which is meant to support developers willing to build explainable MAS leveraging our protocol. Finally, we discuss how custom notions of recommendation and explanation can be easily plugged into PyXMas.

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 6634
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 8293
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.

    https://spade-mas.readthedocs.io.

  2. 2.

    https://github.com/pikalab-unibo/pyxmas.

References

  1. Barredo Arrieta, A., et al.: Explainable explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020). https://doi.org/10.1016/j.inffus.2019.12.012

    Article  Google Scholar 

  2. Bellifemine, F.L., Caire, G., Greenwood, D.: Developing Multi-Agent Systems with JADE. Wiley, Hoboken (2007). http://eu.wiley.com/WileyCDA/WileyTitle/productCd-0470057475.html

  3. Buzcu, B., Varadhajaran, V., Tchappi, I., Najjar, A., Calvaresi, D., Aydogan, R.: Explanation-based negotiation protocol for nutrition virtual coaching. In: Aydogan, R., Criado, N., Lang, J., Sánchez-Anguix, V., Serramia, M. (eds.) PRIMA 2022: Principles and Practice of Multi-Agent Systems - 24th International Conference, Valencia, Spain, 16–18 November 2022, Proceedings. Lecture Notes in Computer Science, vol. 13753, pp. 20–36. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-21203-1_2

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

    Article  Google Scholar 

  5. Calvaresi, D., et al.: Expectation: personalized explainable artificial intelligence for decentralized agents with heterogeneous knowledge. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds.) EXTRAAMAS 2021. LNCS (LNAI), vol. 12688, pp. 331–343. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-82017-6_20

    Chapter  Google Scholar 

  6. Christakopoulou, K., Radlinski, F., Hofmann, K.: Towards conversational recommender systems. In: KDD 2016: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 815–824 (2016). https://doi.org/10.1145/2939672.2939746

  7. Ciatto, G., Calegari, R., Omicini, A., Calvaresi, D.: Towards XMAS: eXplainability through multi-agent systems. In: Savaglio, C., Fortino, G., Ciatto, G., Omicini, A. (eds.) AI &IoT 2019 - Artificial Intelligence and Internet of Things 2019, CEUR Workshop Proceedings, vol. 2502, pp. 40–53. Sun SITE Central Europe, RWTH Aachen University (2019). http://ceur-ws.org/Vol-2502/paper3.pdf

  8. Ciatto, G., Schumacher, M.I., Omicini, A., Calvaresi, D.: Agent-based explanations in AI: towards an abstract framework. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds.) EXTRAAMAS 2020. LNCS (LNAI), vol. 12175, pp. 3–20. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-51924-7_1

    Chapter  Google Scholar 

  9. Fielding, R.T., Taylor, R.N.: Principled design of the modern Web architecture. ACM Trans. Internet Technol. 2(2), 115–150 (2002). https://doi.org/10.1145/514183.514185

    Article  Google Scholar 

  10. 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 (2018). https://doi.org/10.1145/3236009

  11. Gunning, D.: Explainable artificial intelligence (XAI). Funding Program DARPA-BAA-16-53, DARPA (2016). http://www.darpa.mil/program/explainable-artificial-intelligence

  12. Knijnenburg, B.P., Willemsen, M.C., Hirtbach, S.: Receiving recommendations and providing feedback: the user-experience of a recommender system. In: Buccafurri, F., Semeraro, G. (eds.) EC-Web 2010. LNBIP, vol. 61, pp. 207–216. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15208-5_19

    Chapter  Google Scholar 

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

    Article  Google Scholar 

  14. Magnini, M., Ciatto, G., Omicini, A.: 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, 4th International Workshop, EXTRAAMAS 2022, Virtual Event, Revised Selected Papers, Lecture Notes in Computer Science, 9–10 May 2022, vol. 13283, chap. 6, pp. 90–108. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-15565-9_6

  15. Millecamp, M., Htun, N.N., Conati, C., Verbert, K.: To explain or not to explain: The effects of personal characteristics when explaining music recommendations. In: IUI 2019: Proceedings of the 24th International Conference on Intelligent User Interfaces, pp. 397–407. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3301275.3302313

  16. Mualla, Y., et al.: The quest of parsimonious XAI: a human-agent architecture for explanation formulation. Artif. Intell. 302, 103573 (2022). https://doi.org/10.1016/j.artint.2021.103573

    Article  MathSciNet  MATH  Google Scholar 

  17. O’Donovan, J., Smyth, B., Gretarsson, B., Bostandjiev, S., Höllerer, T.: PeerChooser: visual interactive recommendation. In: CHI 2008: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1085–1088 (2008). https://doi.org/10.1145/1357054.1357222

  18. Omicini, A.: Not just for humans: explanation for agent-to-agent communication. In: Vizzari, G., Palmonari, M., Orlandini, A. (eds.) AIxIA 2020 DP – AIxIA 2020 Discussion Papers Workshop. AI*IA Series, vol. 2776, pp. 1–11. Sun SITE Central Europe, RWTH Aachen University, Aachen (2020). http://ceur-ws.org/Vol-2776/paper-1.pdf

  19. Sabbatini, F., Ciatto, G., Calegari, R., Omicini, A.: Symbolic knowledge extraction from opaque ML predictors in PSyKE: platform design & experiments. Intelligenza Artificiale 16(1), 27–48 (2022). https://doi.org/10.3233/IA-210120

    Article  Google Scholar 

  20. Shimazu, H.: ExpertClerk: a conversational case-based reasoning tool for developing salesclerk agents in e-commerce webshops. Artif. Intell. Rev. 18, 223–244 (2002). https://doi.org/10.1023/A:1020757023711

    Article  Google Scholar 

  21. Zhang, Y., Chen, X.: Explainable recommendation: a survey and new perspectives. Found. Trends Inf. Retr. 17(1), 1–101 (2020). https://doi.org/10.1561/1500000066

    Article  Google Scholar 

Download references

Acknowledgements

This work has been supported by the Chist-Era IV project “Expectation”, the Italian Ministry for Universities and Research (G.A. CHIST-ERA-19-XAI-005), and by the Scientific and Research Council of Turkey (TÜBİTAK, G.A. 120N680).

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering (DISI), Alma Mater Studiorum – Università di Bologna, via dell’Università 50, 47522, Cesena, FC, Italy

    Giovanni Ciatto, Matteo Magnini & Andrea Omicini

  2. Department of Computer Science, Özyeğin University, Nisantepe Mah. Orman Sok. No: 34-36 Alemdağ, Çekmeköy, 34794, Istanbul, Turkey

    Berk Buzcu & Reyhan Aydoğan

  3. Interactive Intelligence, Delft University of Technology, Mekelweg 4, 2628 CD, Delft, The Netherlands

    Reyhan Aydoğan

Authors
  1. Giovanni Ciatto
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Matteo Magnini
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Berk Buzcu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Reyhan Aydoğan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Andrea Omicini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Giovanni Ciatto .

Editor information

Editors and Affiliations

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

    Davide Calvaresi

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

    Amro Najjar

  3. Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    Andrea Omicini

  4. Ozyegin University, Istanbul, Türkiye

    Reyhan Aydogan

  5. Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    Rachele Carli

  6. Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    Giovanni Ciatto

  7. Université de Technologie de Belfort-Montbéliard, Belfort Cedex, France

    Yazan Mualla

  8. Umeå University, Umeå, Sweden

    Kary Främling

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Ciatto, G., Magnini, M., Buzcu, B., Aydoğan, R., Omicini, A. (2023). A General-Purpose Protocol for Multi-agent Based Explanations. In: Calvaresi, D., et al. Explainable and Transparent AI and Multi-Agent Systems. EXTRAAMAS 2023. Lecture Notes in Computer Science(), vol 14127. Springer, Cham. https://doi.org/10.1007/978-3-031-40878-6_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-40878-6_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-40877-9

  • Online ISBN: 978-3-031-40878-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation