Unknown
Adaptive user-interfaces (AUIs) can enhance the usability of complex software by providing real-time contextual adapta- tion and assistance. Ideally, AUIs should be personalized and versatile, i.e., able to adapt to each user who may perform a variety of complex tasks. But this is difficult to achieve with many interaction elements when data-per-user is sparse. In this paper, we propose an architecture for personalized AUIs that leverages upon developments in (1) deep learning, par- ticularly gated recurrent units, to efficiently learn user inter- action patterns, (2) collaborative filtering techniques that en- able sharing of data among users, and (3) fast approximate nearest-neighbor methods in Euclidean spaces for quick UI control and/or content recommendations. Specifically, inter- action histories are embedded in a learned space along with users and interaction elements; this allows the AUI to query and recommend likely next actions based on similar usage patterns across the user base. In a comparative evaluation on user-interface, web-browsing and e-learning datasets, the deep recurrent neural-network (DRNN) outperforms state-of- the-art tensor-factorization and metric embedding methods. Author Keywords Adaptive User Interface; Deep Learning; Personalization ACM Classification Keywords I.2.6. Artificial Intelligence: Learning; H.5.2 Information In- terfaces and Presentation(e.g. HCI): User Interfaces