2018

Contrastive Explanation: A Structural-Model Approach

Miller, Tim

Understand

This paper presents a model of contrastive explanation using structural casual models.

The topic of causal explanation in artificial intelligence has gathered interest in recent years as researchers and practitioners aim to increase trust and understanding of intelligent decision-making.
While different sub-fields of artificial intelligence have looked into this problem with a sub-field-specific view, there are few models that aim to capture explanation more generally.
One general model is based on structural causal models.

Built on

Why–questions
Sylvain Bromberger · 1966
Earlier work this paper cites.
Logic and conversation
Herbert P Grice · 1975
Earlier work this paper cites.
The scientific image
Bas C Van Fraassen · 1980
Earlier work this paper cites.
Forms of explanation: Rethinking the questions in social theory
Alan Garfinkel · 1981
Earlier work this paper cites.
Explaining differences and weighting causes
Germund Hesslow · 1983
Earlier work this paper cites.
Rule-based expert systems: the MYCIN experiments of the Stanford Heuristic Programming Project
Bruce Buchanan and Edward Shortliffe · 1984
Earlier work this paper cites.
Causal explanation
David Lewis · 1986
Earlier work this paper cites.
Explaining contrastive facts
David-Hillel Ruben · 1987
Earlier work this paper cites.
The problem of causal selection
Germund Hesslow · 1988
Earlier work this paper cites.
The contrast theory of why–questions
Dennis Temple · 1988
Earlier work this paper cites.
Explaining control strategies in problem solving
B Chandrasekaran, Michael C. Tanner, and John R. Josephson · 1989
Earlier work this paper cites.
Conversational processes and causal explanation
Denis J Hilton · 1990
Earlier work this paper cites.
Contrastive explanation
Peter Lipton · 1990
Earlier work this paper cites.

Similar

Attribution in conversational context: Effect of mutual knowledge on explanation-giving
Ben R Slugoski, Mansur Lalljee, Roger Lamb, and Gerald P Ginsburg · 1993
Cited alongside, same era.
Explanation in second generation expert systems
William R Swartout and Johanna D Moore · 1993
Cited alongside, same era.
A characterization of contrastive explanations computation
Alex Kean · 1998
Cited alongside, same era.
Remote causes, bad explanations?
Jeroen Van Bouwel and Erik Weber · 2002
Cited alongside, same era.
Human-automation collaboration in dynamic mission planning: A challenge requiring an ecological approach
Michael P Linegang, Heather A Stoner, Michael J Patterson, Bobbie D Seppelt, Joshua D Hoffman, Zachariah B Crittendon, and John D Lee · 2006
Cited alongside, same era.
Autonomy and common ground in human-robot interaction: A field study
K. Stubbs, P. Hinds, and D. Wettergreen · 2007
Cited alongside, same era.
The idea of contrastive explanandum
Petri Ylikoski · 2007
Cited alongside, same era.
Designs for explaining intelligent agents
Steven R Haynes, Mark A Cohen, and Frank E Ritter · 2009
Cited alongside, same era.
Assessing demand for intelligibility in context-aware applications
Brian Y Lim and Anind K Dey · 2009
Cited alongside, same era.
A modification of the halpern-pearl definition of causality
Joseph Y Halpern · 2015
Cited alongside, same era.
Machine bias
Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner · 2016
Cited alongside, same era.
Intelligent agent transparency in human–agent teaming for multi-uxv management
Joseph E Mercado, Michael A Rupp, Jessie YC Chen, Michael J Barnes, Daniel Barber, and Katelyn Procci · 2016
Cited alongside, same era.

Then

Contrastive constraints guide explanation-based category learning
Seth Chin-Parker and Julie Cantelon · 2017
Later among the works it cites.
Counterfactual explanations without opening the black box: Automated decisions and the gdpr
Sandra Wachter, Brent Mittelstadt, and Chris Russell · 2017
Later among the works it cites.
Debugging agent programs with Why?: Questions
Michael Winikoff · 2017
Later among the works it cites.
Explanations based on the missing: Towards contrastive explanations with pertinent negatives
Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, and Payel Das · 2018
Closest in time.
Explanation in artificial intelligence: Insights from the social sciences
Original
Tim Miller · 2018
Closest in time.
Hierarchical expertise level modeling for user specific contrastive explanations
Sarath Sreedharan, Siddharth Srivastava, and Subbarao Kambhampati · 2018
Closest in time.
Contrastive explanations for reinforcement learning in terms of expected consequences
J Waa, J van Diggelen, K Bosch, and M Neerincx · 2018
Closest in time.
Model-based contrastive explanations for explainable planning
Benjamin Krarup, Michael Cashmore, Daniele Magazzeni, and Tim Miller · 2019
Closest in time.
Designing theory-driven user-centric explainable ai
Danding Wang, Qian Yang, Ashraf Abdul, and Brian Y Lim · 2019
Closest in time.
CoCoX: Generating conceptual and counterfactual explanations via fault-lines
Arjun R Akula, Shuai Wang, and Song-Chun Zhu · 2020
Closest in time.
Explainable reinforcement learning through a causal lens
Prashan Madumal, Tim Miller, Liz Sonenberg, and Frank Vetere · 2020
Closest in time.
Explaining machine learning classifiers through diverse counterfactual explanations
Ramaravind K Mothilal, Amit Sharma, and Chenhao Tan · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…