Explainability methods
0 likes206 views
The document discusses explainable AI (XAI) methods. It defines XAI both narrowly as techniques that explain model decisions and broadly as anything that increases AI understandability. The document outlines intrinsically interpretable and post-hoc explanation methods like LIME and SHAP that explain complex models. It emphasizes the importance of explanations being actionable, contextualized and developed with stakeholder input. The document presents examples of XAI dashboards and concludes with recommendations to involve end-users and provide personalized, simplified explanations.
Explainability methods
- 1. Explainability methods Flanders AI Forum – 6 June 2023 Katrien Verbert Augment/HCI – Department of Computer Science – KU Leuven @katrien_v https://augment.cs.kuleuven.be
- 2. What is explainable AI? And why does it matter? 2 Src: https://www.ai4science.caltech.edu/xai
- 3. Explainable Artificial Intelligence (XAI) Narrow definition Techniques and methods that make a model’s decision understandable by people Broad definition Everything that makes AI understandable (e.g. also including data, functions, performance, etc.) 3 Src: Vera Liao
- 4. 4 https://hbr.org/2019/10/ai-can-outperform-doctors-so-why-dont-patients-trust-it
- 5. 5 Bhattacharya, A. (2022). Applied Machine Learning Explainability Techniques: Make ML models explainable and trustworthy for practical applications using LIME, SHAP, and more. Packt Publishing Ltd.
- 6. “Black box” approach does not work 6 Illustration: Erik Blad for The Intercept
- 7. Five ways XAI can benefit organisations 7 https://www.mckinsey.com/capabilities/quantumblack/our-insights/why-businesses-need- explainable-ai-and-how-to-deliver-it Technologists 1. More efficiently monitor, maintain, and improve AI systems Business professionals 2. Trust AI outputs, so they increasingly adopt AI tools 3. Apply knowledge about the why of an AI prediction or recommendation to identify effective interventions 4. Asess whether AI applications meet business objectives Legal and risk professionals 5. See whether technology and associated workflows comply with applicable regulations and are in line with customer expectations
- 8. 8 Stiglic, G., Kocbek, P., Fijacko, N., Zitnik, M., Verbert, K., & Cilar, L. (2020). Interpretability of machine learning-based prediction models in healthcare. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(5), e1379.
- 9. Intrinsically interpretable AI models 9
- 10. Intrinsically interpretable AI models 10
- 11. Explanation methods for complex models 11 Feature importance methods Example- based explanations
- 12. LIME 12
- 13. LIME 13
- 14. SHapley Additive exPlanations (SHAP) 14
- 16. Counterfactual explanations ¤ A counterfactual explanation describes a causal situation in the form: “If X had not occurred, Y would not have occurred” ¤ A counterfactual explanation of a prediction describes the smallest change to the feature values that changes the prediction to a predefined output. ¤ There are both model-agnostic and model-specific counterfactual explanation methods 16 Example: You were denied a loan because your annual income is €30.000. If your income had been €45,000, you would have been offered a loan.
- 17. Open Challenges in XAI ¤ Difficult to understand visualisations for non-expert users ¤ Lack of stakeholder participation ¤ Lack of actionable explanations ¤ Lack of contextual explanations 17
- 18. Learning analytics & human resources Media consumption Wellbeing, food & health Precision agriculture FinTech & Insurtech human-centered XAI
- 19. 19
- 20. Dashboard for health professionals 20
- 24. 24 Explanations for end users Word cloud Feature importance Feature importance+ % Maxwell Szymanski, Vero Vanden Abeele and Katrien Verbert Explaining health recommendations to lay users: The dos and don’ts – Apex-IUI 2022
- 25. Why do users (dis)like the explanation? 25
- 26. Textual, visual or hybrid? 26
- 27. Results ¤ Hybrid explanations more useful compared to both the textual and visual explanations. ¤ Users with a higher NFC tend to score the hybrid explanations lower in terms of trust, transparency and usefulness compared to the unimodal explanation. 27
- 28. 28
- 29. 29 Charleer S., Gutiérrez Hernández F., Verbert K. (2019). Supporting job mediator and job seeker through an actionable dashboard. In: Proceedings of the 24th IUI conference on Intelligent User Interfaces Presented at the ACM IUI 2019 Actionable explanations
- 30. Model behaviour Rojo, D., Htun, N. N., Parra, D., De Croon, R., & Verbert, K. (2021). AHMoSe: A knowledge-based visual support system for selecting regression machine learning models. Computers and Electronics in Agriculture, 187, 106183.
- 31. Model behaviour 31 Model Explanations (SHAP) Model + Knowledge Summary
- 32. 32 Bhattacharya, A., Ooge, J., Stiglic, G., & Verbert, K. (2023, March). Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations. In Proceedings of the 28th International Conference on Intelligent User Interfaces (pp. 204-219). Bhattacharya, A., Ooge, J., Stiglic, G., & Verbert, K. (2023, March). Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations. In Proceedings of the 28th International Conference on Intelligent User Interfaces (pp. 204-219). Data-centric explanations
- 33. Some take-away messages ¤ Involvement of end-users is key to come up with interfaces tailored to the needs of non-expert users ¤ Actionable vs non-actionable parameters ¤ Data-centric explanations provide powerful solution ¤ Interaction is powerful to support model understanding ¤ Need for personalisation and simplification 33
- 34. How to get started? 34