Kilian Kluge @ PyData Global 2022, December 1st, 12:00 UTC, Track II
Methods and techniques from the realm of artificial intelligence (AI), such as machine learning, find their way into ever more software and devices. As more people interact with these highly complex and opaque systems in their private and professional lives, there is a rising need to communicate AI-based decisions, predictions, and recommendations to their users.
So-called “interpretability” or “explainability” methods claim to allow insights into the proverbial “black boxes.” Many data scientists use tools like SHAP, LIME, or partial dependence plots in their day-to-day work to analyze and debug models.
However, as numerous studies have shown, even experienced data scientists are prone to interpret the “explanations” generated by these tools in ways that support their pre-existing beliefs. This problem becomes even more severe when “explanations” are presented to end-users in hopes of allowing them to assess and scrutinize an AI system’s output.
In this talk, we’ll explore the problem space using the example of counterfactual explanations for price estimates. Participants will learn how to employ user studies and principles from human-centric design to implement “explanations” that fulfill their purpose.
No prior data science knowledge is required to follow the talk, but a basic familiarity with the concept of minimizing an objective function will be helpful.
- Pacer & Lombrozo (2017): Ockham’s Razor Cuts to the Root: Simplicity in Causal Explanation doi:10.1037/xge0000318
- Miller (2019): Explanation in artificial intelligence: Insights from the social sciences doi:10.1016/j.artint.2018.07.007
- Doshi-Velez & Kim (2017): Towards A Rigorous Science of Interpretable Machine Learning arXiv:1702.08608
- Förster et al. (2020): Evaluating Explainable Artifical Intelligence – What Users Really Appreciate ECIS 2020 Proceedings
- Förster et al. (2020): Fostering Human Agency: A Process for the Design of UserCentric XAI Systems ICIS 2020 Proceedings
- Keane (2021): If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
- Lakkaraju & Bastani (2020): "How Do I Fool You?": Manipulating User Trust via Misleading Black Box Explanations. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Kaur et al. (2020): Interpreting Interpretability: Understanding Data Scientists’ Use of Interpretability Tools for Machine Learning Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Verma et al. (2022): Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review arXiv:2010.10596
- Förster et al. (2021): Capturing Users’ Reality: A Novel Approach to Generate Coherent Counterfactual Explanations Proceedings of the 54th Hawaii International Conference on System Sciences
- Förster et al. (2022): User-centric explainable AI: design and evaluation of an approach to generate coherent counterfactual explanations for structured data doi:10.1080/12460125.2022.2119707
- Invite Link
- If the link is no longer valid, send a message to @XAI_Research on Twitter or explainableaiworld AT gmail DOT com to receive an invite