Personalized Explanation for Machine Learning: a Conceptualization

Explanation in machine learning and related fields such as artificial intelligence aims at making machine learning models and their decisions understandable to humans. Existing work suggests that personalizing explanations might help to improve understandability. In this work, we derive a conceptualization of personalized explanation by defining and structuring the problem based on prior work on machine learning explanation, personalization (in machine learning) and concepts and techniques from other domains such as privacy and knowledge elicitation. We perform a categorization of explainee data used in the process of personalization as well as describing means to collect this data. We also identify three key explanation properties that are amendable to personalization: complexity, decision information and presentation. We also enhance existing work on explanation by introducing additional desiderata and measures to quantify the quality of personalized explanations.

[1]  Hsinchun Chen,et al.  Web mining: Machine learning for web applications , 2005, Annu. Rev. Inf. Sci. Technol..

[2]  Guokun Lai,et al.  Explicit factor models for explainable recommendation based on phrase-level sentiment analysis , 2014, SIGIR.

[3]  Johannes Schneider,et al.  Mining Sequences of Developer Interactions in Visual Studio for Usage Smells , 2017, IEEE Transactions on Software Engineering.

[4]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[5]  Richard T. Watson,et al.  Analyzing the Past to Prepare for the Future: Writing a Literature Review , 2002, MIS Q..

[6]  Alun D. Preece,et al.  Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems , 2018, ArXiv.

[7]  Nada Lavrac,et al.  Selected techniques for data mining in medicine , 1999, Artif. Intell. Medicine.

[8]  Samuel J. Gershman,et al.  Human-in-the-Loop Interpretability Prior , 2018, NeurIPS.

[9]  Quanshi Zhang,et al.  Interpretable Convolutional Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[11]  Brad Boehmke,et al.  Interpretable Machine Learning , 2019 .

[12]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[13]  Marshall Scott Poole,et al.  What Is Personalization? Perspectives on the Design and Implementation of Personalization in Information Systems , 2006, J. Organ. Comput. Electron. Commer..

[14]  Mike Wu,et al.  Beyond Sparsity: Tree Regularization of Deep Models for Interpretability , 2017, AAAI.

[15]  Mayuram S. Krishnan,et al.  The Personalization Privacy Paradox: An Empirical Evaluation of Information Transparency and the Willingness to be Profiled Online for Personalization , 2006, MIS Q..

[16]  Yang Wang,et al.  Personalization and privacy: a survey of privacy risks and remedies in personalization-based systems , 2012, User Modeling and User-Adapted Interaction.

[17]  Juan A. Recio-García,et al.  Make it personal: A social explanation system applied to group recommendations , 2017, Expert Syst. Appl..

[18]  Mary Beth Rosson,et al.  The personalization privacy paradox: An exploratory study of decision making process for location-aware marketing , 2011, Decis. Support Syst..

[19]  Maya Cakmak,et al.  Power to the People: The Role of Humans in Interactive Machine Learning , 2014, AI Mag..

[20]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

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

[22]  Y. I. Liou,et al.  Knowledge acquisition: issues, techniques and methodology , 1992, DATB.

[23]  William R. King,et al.  Understanding the Role and Methods of Meta-Analysis in IS Research , 2005, Commun. Assoc. Inf. Syst..

[24]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[25]  Bart Baesens,et al.  An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models , 2011, Decis. Support Syst..

[26]  Alexandra Kirsch,et al.  Explain to whom? Putting the User in the Center of Explainable AI , 2017, CEx@AI*IA.

[27]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[28]  Josep Lluís de la Rosa i Esteva,et al.  A Taxonomy of Recommender Agents on the Internet , 2003, Artificial Intelligence Review.

[29]  Peter A. Flach,et al.  Glass-Box: Explaining AI Decisions With Counterfactual Statements Through Conversation With a Voice-enabled Virtual Assistant , 2018, IJCAI.

[30]  Y. de Montjoye,et al.  Unique in the shopping mall: On the reidentifiability of credit card metadata , 2015, Science.

[31]  Xu Chen,et al.  Visually Explainable Recommendation , 2018, ArXiv.

[32]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[33]  Franca Garzotto,et al.  Investigating the Persuasion Potential of Recommender Systems from a Quality Perspective: An Empirical Study , 2012, TIIS.

[34]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[35]  Jerry Alan Fails,et al.  Interactive machine learning , 2003, IUI '03.

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

[37]  Geoffrey I. Webb,et al.  # 2001 Kluwer Academic Publishers. Printed in the Netherlands. Machine Learning for User Modeling , 1999 .

[38]  Arvind Satyanarayan,et al.  The Building Blocks of Interpretability , 2018 .

[39]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..

[40]  Emily Chen,et al.  How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation , 2018, ArXiv.

[41]  Dhruv Batra,et al.  Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions? , 2016, EMNLP.

[42]  Izak Benbasat,et al.  Explanations From Intelligent Systems: Theoretical Foundations and Implications for Practice , 1999, MIS Q..

[43]  Johannes Fürnkranz,et al.  On Cognitive Preferences and the Interpretability of Rule-based Models , 2018, ArXiv.

[44]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

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

[46]  Fred G. W. C. Paas,et al.  The Efficiency of Instructional Conditions: An Approach to Combine Mental Effort and Performance Measures , 1992 .

[47]  Jure Leskovec,et al.  Interpretable & Explorable Approximations of Black Box Models , 2017, ArXiv.

[48]  Marcel van Gerven,et al.  Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges , 2018, ArXiv.

[49]  Cynthia Rudin,et al.  Bayesian Rule Sets for Interpretable Classification , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[50]  M. Bouaziz,et al.  An Introduction to Computer Security , 2012 .

[51]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[52]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[53]  F. Maxwell Harper,et al.  Crowd-Based Personalized Natural Language Explanations for Recommendations , 2016, RecSys.

[54]  Filip Karlo Dosilovic,et al.  Explainable artificial intelligence: A survey , 2018, 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[55]  Daniel G. Goldstein,et al.  Manipulating and Measuring Model Interpretability , 2018, CHI.

[56]  Reuben Binns,et al.  Fairness in Machine Learning: Lessons from Political Philosophy , 2017, FAT.

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

[58]  Marco Basaldella,et al.  Crowdsourcing Relevance Assessments: The Unexpected Benefits of Limiting the Time to Judge , 2016, HCOMP.

[59]  Cordelia Schmid,et al.  Learning object class detectors from weakly annotated video , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[60]  Peter McGeorge,et al.  The uses of ‘contrived’ knowledge elicitation techniques , 1992 .

[61]  David Eckhoff,et al.  Metrics : a Systematic Survey , 2018 .

[62]  Heiko Paulheim,et al.  Generating Possible Interpretations for Statistics from Linked Open Data , 2012, ESWC.

[63]  Martin Wattenberg,et al.  Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) , 2017, ICML.

[64]  Cynthia Rudin,et al.  Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains its Predictions , 2017, AAAI.

[65]  Jan vom Brocke,et al.  Identifying Preferences through mouse cursor movements - Preliminary Evidence , 2017, ECIS.

[66]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[67]  Amit Dhurandhar,et al.  Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives , 2018, NeurIPS.

[68]  Xu Chen,et al.  Explainable Recommendation: A Survey and New Perspectives , 2018, Found. Trends Inf. Retr..

[69]  Anind K. Dey,et al.  Why and why not explanations improve the intelligibility of context-aware intelligent systems , 2009, CHI.

[70]  N. Shadbolt,et al.  Eliciting Knowledge from Experts: A Methodological Analysis , 1995 .

[71]  Ricardo Buettner,et al.  Cognitive Workload of Humans Using Artificial Intelligence Systems: Towards Objective Measurement Applying Eye-Tracking Technology , 2013, KI.

[72]  Been Kim,et al.  Sanity Checks for Saliency Maps , 2018, NeurIPS.

[73]  Li Chen,et al.  Survey of Preference Elicitation Methods , 2004 .

[74]  Jeff Tian,et al.  Improving Web Navigation Usability by Comparing Actual and Anticipated Usage , 2015, IEEE Transactions on Human-Machine Systems.