Tutorial on Towards Better Explainable AI Through Genetic Programming
The IEEE World Congress on Computational Intelligence
18-23 July 2021, Padova, Italy
Although machine learning has achieved great success in many real-world applications, it is criticised as usually behaving like a black box, and it is often difficult, if not impossible, to understand how the machine learning system makes the decision/prediction. This could lead to serious consequences, such as the accidents of the Tesla automatic driving cars, and biases of the automatic bank loan approval systems.
To address this issue, Explainable AI (XAI) is becoming a very hot research topic in the AI field due to its urgent needs in various domains such as finance, security, medical, gaming, legislation, etc. There have been an increasing number of studies on XAI in recent years, which improves the current machine learning systems from different aspects.
In evolutionary computation, Genetic Programming (GP) has been successfully used in various machine learning tasks including classification, symbolic regression, clustering, feature construction, and automatic heuristic design. As a symbolic-based evolutionary learning approach, GP has an intrinsic great potential to contribute to XAI, as a GP model tends to be interpretable.
This tutorial will give a brief introduction on the common approaches in XAI, such as attention map, post-hoc explanation (LIME, SHAP), visualisation, and then introduce how to approach better model interpretability through GP, including multi-objective GP, simplification in GP, different representations in GP, and post-hoc explanation using GP. Finally, we will discuss the current trend, challenges and potential future research directions.
This tutorial will be composed of the following parts:
- Brief introduction to XAI
- Attention/heat map
- Post-hoc explanation
- Brief introduction to GP
- How to approach better model interpretability through GP [50 mins]
- Multi-Objective GP
- Dimensionality Aware GP
- Ensemble GP
- Simplification in GP
- Grammar-based GP
- Post-hoc explanation using GP
- Challenges and Future Directions
Dr. Yi Mei, Victoria University of Wellington, New Zealand (email@example.com)
Dr. Yi Mei (M’09-SM’18) is a Senior Lecturer at the School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand. He received his BSc and PhD degrees from University of Science and Technology of China in 2005 and 2010, respectively. His research interests include evolutionary computation in scheduling, routing and combinatorial optimisation, as well as evolutionary machine learning, hyper-heuristics, genetic programming, feature selection and dimensional reduction.
Yi has more than 100 fully referred publications, including the top journals in EC and Operations Research (OR) such as IEEE TEVC, IEEE Transactions on Cybernetics, European Journal of Operational Research, ACM Transactions on Mathematical Software, and top EC conferences (GECCO). He won an IEEE Transactions on Evolutionary Computation Outstanding Paper Award 2017, and a Victoria University of Wellington Early Research Excellence Award 2018. As the sole investigator, he won the 2nd prize of the Competition at IEEE WCCI 2014: Optimisation of Problems with Multiple Interdependent Components. He serves as a Vice-Chair of the IEEE CIS Emergent Technologies Technical Committee, and a member of three IEEE CIS Task Forces and two IEEE CIS Technical Committees. He is an Editorial Board Member of International Journal of Bio-Inspired Computation, an Associate Editor of International Journal of Applied Evolutionary Computation and International Journal of Automation and Control, and a guest editor of a special issue of the Genetic Programming Evolvable Machine journal. He has organised a number of special sessions in international conferences such as IEEE CEC. He serves as a reviewer of over 30 international journals including the top journals in EC and OR. He was an Outstanding Reviewer for Applied Soft Computing in 2015 and 2017, and IEEE Transactions on Cybernetics in 2018.
Dr. Andrew Lensen, Victoria University of Wellington, New Zealand (firstname.lastname@example.org)