Differentiable user models

Loading...
Thumbnail Image
Access rights
openAccess
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2023-08
Major/Subject
Mcode
Degree programme
Language
en
Pages
798-808
Series
Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023), Proceedings of Machine Learning Research, Volume 216
Abstract
Probabilistic user modeling is essential for building machine learning systems in the ubiquitous cases with humans in the loop. However, modern advanced user models, often designed as cognitive behavior simulators, are incompatible with modern machine learning pipelines and computationally prohibitive for most practical applications. We address this problem by introducing widely-applicable differentiable surrogates for bypassing this computational bottleneck; the surrogates enable computationally efficient inference with modern cognitive models. We show experimentally that modeling capabilities comparable to the only available solution, existing likelihood-free inference methods, are achievable with a computational cost suitable for online applications. Finally, we demonstrate how AI-assistants can now use cognitive models for online interaction in a menu-search task, which has so far required hours of computation during interaction.
Description
| openaire: EC/H2020/951847/EU//ELISE | openaire: EC/H2020/952026/EU//HumanE-AI-Net
Keywords
Other note
Citation
Hämäläinen, A, Celikok, M M & Kaski, S 2023, Differentiable user models . in Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023) . vol. 216, Proceedings of Machine Learning Research, vol. 216, JMLR, pp. 798-808, Conference on Uncertainty in Artificial Intelligence, Pittsburgh, Pennsylvania, United States, 31/07/2023 . < https://proceedings.mlr.press/v216/hamalainen23a.html >