ABSTRACT
The black-box nature of machine learning algorithms can make their predictions difficult to understand and explain to end-users. In this paper, we propose and evaluate two kinds of example-based explanations in the visual domain, normative explanations and comparative explanations (Figure 1), which automatically surface examples from the training set of a deep neural net sketch-recognition algorithm. To investigate their effects, we deployed these explanations to 1150 users on QuickDraw, an online platform where users draw images and see whether a recognizer has correctly guessed the intended drawing. When the algorithm failed to recognize the drawing, those who received normative explanations felt they had a better understanding of the system, and perceived the system to have higher capability. However, comparative explanations did not always improve perceptions of the algorithm, possibly because they sometimes exposed limitations of the algorithm and may have led to surprise. These findings suggest that examples can serve as a vehicle for explaining algorithmic behavior, but point to relative advantages and disadvantages of using different kinds of examples, depending on the goal.
- Ashraf Abdul, Jo Vermeulen, Danding Wang, Brian Y Lim, and Mohan Kankanhalli. 2018. Trends and trajectories for explainable, accountable and intelligible systems: An hci research agenda. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. ACM, 582. Google ScholarDigital Library
- Carrie J Cai. 2013. Adapting arcade games for learning. In CHI'13 Extended Abstracts on Human Factors in Computing Systems. ACM, 2665--2670. Google ScholarDigital Library
- Carrie J Cai, Emily Reif, Narayan Hegde, Jason Hipp, Been Kim, Daniel Smilkov, Martin Wattenberg, Fernanda Viegas, Greg S Corrado, Martin C Stumpe, and Michael Terry. 2019. Refinement Tools for Coping with Imperfect Algorithms during Medical Decision-Making. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. ACM.Google ScholarDigital Library
- Matteo Colombo, Leandra Bucher, and Jan Sprenger. 2017. Determinants of judgments of explanatory power: Credibility, Generality, and Statistical Relevance. Frontiers in psychology 8 (2017), 1430.Google Scholar
- Malin Eiband, Hanna Schneider, Mark Bilandzic, Julian Fazekas-Con, Mareike Haug, and Heinrich Hussmann. 2018. Bringing Transparency Design into Practice. In 23rd International Conference on Intelligent User Interfaces. ACM, 211--223. Google ScholarDigital Library
- Dumitru Erhan, Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2009. Visualizing higher-layer features of a deep network. University of Montreal 1341, 3 (2009), 1.Google Scholar
- Motahhare Eslami, Karrie Karahalios, Christian Sandvig, Kristen Vaccaro, Aimee Rickman, Kevin Hamilton, and Alex Kirlik. 2016. First i like it, then i hide it: Folk theories of social feeds. In Proceedings of the 2016 cHI conference on human factors in computing systems. ACM, 2371--2382. Google ScholarDigital Library
- Motahhare Eslami, Sneha R Krishna Kumaran, Christian Sandvig, and Karrie Karahalios. 2018. Communicating Algorithmic Process in Online Behavioral Advertising. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. ACM, 432. Google ScholarDigital Library
- Bryce Goodman and Seth Flaxman. 2016. European Union regulations on algorithmic decision-making and a" right to explanation". arXiv preprint arXiv:1606.08813 (2016).Google Scholar
- Jonathan L Herlocker, Joseph A Konstan, and John Riedl. 2000. Explaining collaborative filtering recommendations. In Proceedings of the 2000 ACM conference on Computer supported cooperative work. ACM, 241--250. Google ScholarDigital Library
- Daniel Keysers, Thomas Deselaers, Henry A Rowley, Li-Lun Wang, and Victor Carbune. 2017. Multi-Language Online Handwriting Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39, 6 (2017), 1180--1194. Google ScholarDigital Library
- Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In International Conference on Machine Learning. 2673--2682.Google Scholar
- René F Kizilcec. 2016. How much information?: Effects of transparency on trust in an algorithmic interface. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems. ACM, 2390--2395. Google ScholarDigital Library
- Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. arXiv preprint arXiv:1703.04730 (2017).Google Scholar
- Todd Kulesza, Simone Stumpf, Margaret Burnett, and Irwin Kwan. 2012. Tell me more?: the effects of mental model soundness on personalizing an intelligent agent. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 1--10. Google ScholarDigital Library
- Brian Y Lim and Anind K Dey. 2009. Assessing demand for intelligibility in context-aware applications. In Proceedings of the 11th international conference on Ubiquitous computing. ACM, 195--204. Google ScholarDigital Library
- Brian Y Lim, Anind K Dey, and Daniel Avrahami. 2009. Why and why not explanations improve the intelligibility of context-aware intelligent systems. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 2119--2128. Google ScholarDigital Library
- Bertram F Malle. 2011. Attribution theories: How people make sense of behavior. Theories in social psychology 23 (2011), 72--95.Google Scholar
- David Martens and Foster Provost. 2013. Explaining data-driven document classifications. (2013).Google Scholar
- Roger C Mayer, James H Davis, and F David Schoorman. 1995. An integrative model of organizational trust. Academy of management review 20, 3 (1995), 709--734.Google Scholar
- Tim Miller. 2017. Explanation in artificial intelligence: insights from the social sciences. arXiv preprint arXiv:1706.07269 (2017).Google Scholar
- Pearl Pu and Li Chen. 2006. Trust building with explanation interfaces. In Proceedings of the 11th international conference on Intelligent user interfaces. ACM, 93--100. Google ScholarDigital Library
- Emilee Rader, Kelley Cotter, and Janghee Cho. 2018. Explanations as Mechanisms for Supporting Algorithmic Transparency. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. ACM, 103. Google ScholarDigital Library
- Stephen J Read and Amy Marcus-Newhall. 1993. Explanatory coherence in social explanations: A parallel distributed processing account. Journal of Personality and Social Psychology 65, 3 (1993), 429.Google ScholarCross Ref
- Alexander Renkl. 2014. Toward an instructionally oriented theory of example-based learning. Cognitive science 38, 1 (2014), 1--37.Google Scholar
- Alexander Renkl, Tatjana Hilbert, and Silke Schworm. 2009. Example-based learning in heuristic domains: A cognitive load theory account. Educational Psychology Review 21, 1 (2009), 67--78.Google ScholarCross Ref
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 1135--1144. Google ScholarDigital Library
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High-precision model-agnostic explanations. In AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- James Schaffer, Prasanna Giridhar, Debra Jones, Tobias Höllerer, Tarek Abdelzaher, and John O'Donovan. 2015. Getting the message?: A study of explanation interfaces for microblog data analysis. In Proceedings of the 20th International Conference on Intelligent User Interfaces. ACM, 345--356. Google ScholarDigital Library
- Kelly G Shaver. 2012. The attribution of blame: Causality, responsibility, and blameworthiness. Springer Science & Business Media.Google Scholar
- Muzafer Sherif. 1936. The psychology of social norms. (1936).Google Scholar
- Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Viégas, and Martin Wattenberg. 2017. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017).Google Scholar
- Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. (2017).Google Scholar
Index Terms
- The effects of example-based explanations in a machine learning interface
Recommendations
“That's (not) the output I expected!” On the role of end user expectations in creating explanations of AI systems
AbstractResearch in the social sciences has shown that expectations are an important factor in explanations as used between humans: rather than explaining the cause of an event per se, the explainer will often address another event that did ...
Directive Explanations for Actionable Explainability in Machine Learning Applications
In this article, we show that explanations of decisions made by machine learning systems can be improved by not only explaining why a decision was made but also explaining how an individual could obtain their desired outcome. We formally define the ...
The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks
Black-box machine learning models are used in an increasing number of high-stakes domains, and this creates a growing need for Explainable AI (XAI). However, the use of XAI in machine learning introduces privacy risks, which currently remain largely ...
Comments