"Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users

Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind queries and predictions is important when assessing how the learner works and, in turn, trust. Consequently, we propose the novel framework of explanatory interactive learning: in each step, the learner explains its interactive query to the user, and she queries of any active classifier for visualizing explanations of the corresponding predictions. We demonstrate that this can boost the predictive and explanatory powers of and the trust into the learned model, using text (e.g. SVMs) and image classification (e.g. neural networks) experiments as well as a user study.

[1]  N. Epley,et al.  The mind in the machine: Anthropomorphism increases trust in an autonomous vehicle , 2014 .

[2]  Christine D. Piatko,et al.  Using “Annotator Rationales” to Improve Machine Learning for Text Categorization , 2007, NAACL.

[3]  Jeffrey M. Bradshaw,et al.  Trust in Automation , 2013, IEEE Intelligent Systems.

[4]  Andrew McCallum,et al.  Toward Optimal Active Learning through Monte Carlo Estimation of Error Reduction , 2001, ICML 2001.

[5]  Maya Cakmak,et al.  Eliciting good teaching from humans for machine learners , 2014, Artif. Intell..

[6]  Carlos Guestrin,et al.  Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.

[7]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[8]  Hema Raghavan,et al.  Active Learning with Feedback on Features and Instances , 2006, J. Mach. Learn. Res..

[9]  Manali Sharma,et al.  Active Learning with Rationales for Text Classification , 2015, NAACL.

[10]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[11]  Ning Wang,et al.  Trust calibration within a human-robot team: Comparing automatically generated explanations , 2016, 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[12]  Susan T. Dumais,et al.  Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration , 2018, WSDM.

[13]  Luc De Raedt,et al.  Probabilistic Explanation Based Learning , 2007, ECML.

[14]  Burr Settles,et al.  Closing the Loop: Fast, Interactive Semi-Supervised Annotation With Queries on Features and Instances , 2011, EMNLP.

[15]  Andreas Krause,et al.  Nonmyopic active learning of Gaussian processes: an exploration-exploitation approach , 2007, ICML '07.

[16]  Osbert Bastani,et al.  Interpreting Blackbox Models via Model Extraction , 2017, ArXiv.

[17]  Zoubin Ghahramani,et al.  Deep Bayesian Active Learning with Image Data , 2017, ICML.

[18]  Thorsten Joachims,et al.  Coactive Learning , 2015, J. Artif. Intell. Res..

[19]  R. Nowak,et al.  Upper and Lower Error Bounds for Active Learning , 2006 .

[20]  Burr Settles,et al.  Active Learning , 2012, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[21]  Foster J. Provost,et al.  A Unified Approach to Active Dual Supervision for Labeling Features and Examples , 2010, ECML/PKDD.

[22]  Paolo Viappiani,et al.  Preferences in Interactive Systems: Technical Challenges and Case Studies , 2008, AI Mag..

[23]  Gabriella Pigozzi,et al.  Preferences in artificial intelligence , 2016, Annals of Mathematics and Artificial Intelligence.

[24]  James Allan,et al.  An interactive algorithm for asking and incorporating feature feedback into support vector machines , 2007, SIGIR.

[25]  Steve Hanneke,et al.  Theory of Disagreement-Based Active Learning , 2014, Found. Trends Mach. Learn..

[26]  Carla E. Brodley,et al.  The Constrained Weight Space SVM: Learning with Ranked Features , 2011, ICML.

[27]  A. Thomaz,et al.  Mixed-Initiative Active Learning , 2012 .

[28]  Jason Eisner,et al.  Modeling Annotators: A Generative Approach to Learning from Annotator Rationales , 2008, EMNLP.

[29]  Andrew Slavin Ross,et al.  Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations , 2017, IJCAI.

[30]  Andrew McCallum,et al.  Active Learning by Labeling Features , 2009, EMNLP.

[31]  Gideon S. Mann,et al.  Learning from labeled features using generalized expectation criteria , 2008, SIGIR '08.

[32]  Li Chen,et al.  Critiquing-based recommenders: survey and emerging trends , 2012, User Modeling and User-Adapted Interaction.

[33]  Thomas G. Dietterich,et al.  Active Imitation Learning via Reduction to I.I.D. Active Learning , 2012, AAAI Fall Symposium: Robots Learning Interactively from Human Teachers.

[34]  Maria-Florina Balcan,et al.  The true sample complexity of active learning , 2010, Machine Learning.

[35]  Cara DiYanni,et al.  ‘I Won't Trust You if I Think You're Trying to Deceive Me': Relations Between Selective Trust, Theory of Mind, and Imitation in Early Childhood , 2012 .

[36]  Weng-Keen Wong,et al.  Principles of Explanatory Debugging to Personalize Interactive Machine Learning , 2015, IUI.

[37]  Gerald DeJong,et al.  Explanation-Based Learning , 2014, Computing Handbook, 3rd ed..

[38]  J. Dessalles,et al.  Arguing, reasoning, and the interpersonal (cultural) functions of human consciousness , 2011, Behavioral and Brain Sciences.

[39]  J. Simpson Psychological Foundations of Trust , 2007 .

[40]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

[41]  Roderick M. Kramer,et al.  Trust and Intergroup Negotiation , 2008 .

[42]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[43]  Holly A. Yanco,et al.  Impact of robot failures and feedback on real-time trust , 2013, 2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[44]  Scott Lundberg,et al.  An unexpected unity among methods for interpreting model predictions , 2016, ArXiv.

[45]  Luke J. Chang,et al.  Seeing is believing: Trustworthiness as a dynamic belief , 2010, Cognitive Psychology.

[46]  Thomas G. Dietterich,et al.  Interacting meaningfully with machine learning systems: Three experiments , 2009, Int. J. Hum. Comput. Stud..