Amortized Inference with User Simulations

要旨

There have been significant advances in simulation models predicting human behavior across various interactive tasks. One issue remains, however: identifying the parameter values that best describe an individual user. These parameters often express personal cognitive and physiological characteristics, and inferring their exact values has significant effects on individual-level predictions. Still, the high complexity of simulation models usually causes parameter inference to consume prohibitively large amounts of time, as much as days per user. We investigated amortized inference for its potential to reduce inference time dramatically, to mere tens of milliseconds. Its principle is to pre-train a neural proxy model for probabilistic inference, using synthetic data simulated from a range of parameter combinations. From examining the efficiency and prediction performance of amortized inference in three challenging cases that involve real-world data (menu search, point-and-click, and touchscreen typing), the paper demonstrates that an amortized inference approach permits analyzing large-scale datasets by means of simulation models. It also addresses emerging opportunities and challenges in applying amortized inference in HCI.

著者
Hee-Seung Moon
Yonsei University, Incheon, Korea, Republic of
Antti Oulasvirta
Aalto University, Helsinki, Finland
Byungjoo Lee
Yonsei University, Seoul, Korea, Republic of
論文URL

https://doi.org/10.1145/3544548.3581439

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: User Behavior Simulation and Modeling

Hall G2
6 件の発表
2023-04-27 18:00:00
2023-04-27 19:30:00