CausalBioCF: Causality and bio-inspired optimization for real-time feasible counterfactual generation

• Gabriel Covello Furlanetto UNESP
• Alexandro Baldassin UNESP
• Aleardo Manacero UNESP

DOI: https://doi.org/10.5753/eradsp.2024.239909

Abstract

Machine learning methods have been widely used to support decision-making, but most of the time the decisions cannot be easily explained. Therefore, providing explanations about the results generated by them becomes important. This is particularly relevant in high-risk decision scenarios in order to protect all the participants. In this work we discuss the parallelization of different styles of algorithms to find contrafactual candidates, an important part of the explainability framework.

References

Cantú-Paz, E. et al. (1998). A survey of parallel genetic algorithms. Calculateurs paralleles, reseaux et systems repartis, 10(2):141–171.

Fatima, M., Pasha, M., et al. (2017). Survey of machine learning algorithms for disease diagnostic. Journal of Intelligent Learning Systems and Applications, 9(01):1.

Gomez-Uribe, C. A. and Hunt, N. (2015). The netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems (TMIS), 6(4):1–19.

Holland, J. H. (1992). Genetic algorithms. Scientific american, 267(1):66–73.

Jin, W. (2020). Research on machine learning and its algorithms and development. In Journal of Physics: Conference Series, volume 1544, page 012003. IOP Publishing.

Karaboga, D. et al. (2005). An idea based on honey bee swarm for numerical optimization. Technical report, Technical report-tr06, Erciyes university, engineering faculty, computer engineering department.

Muthiah, A. and Rajkumar, R. (2014). A comparison of artificial bee colony algorithm and genetic algorithm to minimize the makespan for job shop scheduling. Procedia Engineering, 97:1745–1754.

Narasimhan, H. (2009). Parallel artificial bee colony (pabc) algorithm. In 2009 World congress on nature & biologically inspired computing (NaBIC), pages 306–311. IEEE.

Wachter, S., Mittelstadt, B., and Russell, C. (2017). Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Harv. JL & Tech., 31:841.

Yang, F., Alva, S. S., Chen, J., and Hu, X. (2021). Model-based counterfactual synthesizer for interpretation. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, pages 1964–1974.