Calendar Manager. selected schedule. scheduling request. presentation set. SVM Explainer. explanation. solution set. Constraint Reasoner. PLIANT. SVM meta-information. current profile. 4. 2. 1. 4. 5. 6. 5. 7. 3. preference profile. Explaining Preference Learning Alyssa Glass
Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
Explaining Preference Learning
CS229 Final Project
Computer Science Department, Stanford University
Active Preference Learning in PLIANT
(Yorke-Smith et al. 2007)
Studies of users interacting with systems that learn preferences show that, when the system behaves incorrectly, users quickly lose patience and trust in the system. Even when the system is correct, users view such outcomes as “magical” in some way, but are unable to understand why a particular suggestion is correct, or whether the system is likely to be helpful in the future.
We describe the augmentation of a preference learner to provide meaningful feedback to the user through explanations. This work extends the PLIANT (Preference Learning through Interactive Advisable Nonintrusive Training) SVM-based preference learner, part of the PTIME personalized scheduling assistant in the CALO project.
Model of preferences: aggregation function, a 2-order
Choquet integral over partial utility functions based on the
above features learning 21 coefficient weights:
F(z1, …, zn) = i ai zi + i,j aij (zi zj)
where each zi = ui(xi), the utility for criterion i based on value xi
Evaluation function: combine learned weights with initial
F`(Z) = AZ + (1-)WZ
Each schedule chosen by the user provides information
about a partial preference ordering, as in (Joachims 2002).
Usability and Active Learning
Several user studies show that transparency is key to trusting learning systems:
“The preference model must be explainable to the user … in terms of familiar, domain-relevant concepts.”
Our approach: extend similarity-based explanations to SVM learning
Elicit initial preferences from user (A vector from above)
User specifies new meeting parameters
Constraint solver generates candidate schedules (Z’s)
Candidate schedules ranked using evaluation function, F`(Z)
Candidate schedules presented to user in (roughly) the calculated preference order, with explanations for each one
User can ask questions, then chooses a schedule (Z)
Preferences (ai and aij weights) are updated based on choice
Providing Transparency into Preference Learning
(Work on PML representation and abstraction strategies is on-going; details will be in final report.)
Yorke-Smith, N., Peintner, B., Gervasio, M., and Berry, P. M. Balancing the Needs of Personalization and Reasoning in a User-Centric Scheduling Assistant. Conference on Intelligent User Interfaces 2007 (IUI-07) (to appear).
Berry, P., Gervasio, M., Uribe, T., Pollack, M., and Moffitt, M. A Personalized Time Management Assistant. AAAI Spring Symposium Series, Stanford, CA, March 2005.
Joachims, T. Optimizing Search Engines using Clickthrough Data. Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD), ACM, 2002.
Stumpf, S., Rajaram, V., Li, L., Burnett, M., Dietterich, T., Sullivan, E., Drummond, R., and Herlocker, J. Towards Harnessing User Feedback for Machine Learning. Conference on Intelligent User Interfaces 2007 (IUI-07) (to appear).
We thank Melinda Gervasio, Pauline Berry, Neil Yorke-Smith, and Bart Peintner for access to the PLIANT and PTIME systems, the above architecture picture, and for helpful collaborations, partnerships, and feedback on this work. We also thank Deborah McGuinness, Michael Wolverton, and Paulo Pinheiro da Silva for the IW and PML systems, and for related discussions and previous work that helped to lay the foundation for this effort. We thank Mark Gondek for access to the CALO CLP data, and Karen Myers for related discussions, support, and ideas.