SMAUG: Semantic-Enhanced Mobile App Usage Data Generation With LLM

Abstract

Mobile app usage data reveal user behavioral characteristics and is crucial for mobile operators for network service optimization, but its data collection is pricey and presents privacy concerns. Data synthesis, fortunately, can tackle this barrier by generating diverse and representative artificial datasets that resemble real-world data. In this paper, we propose SMAUG, a diffusion model-based generative model with large language models (LLMs) designed to generate personalized app usage data based on mobile users' mobility trajectories. To address the data inaccuracy issue brought by the sparsity nature of mobile app usage behavior, SMAUG decomposes the generation process and adopts a hierarchical structure framework to gradually refine the generation from the session level to the specific app level. By encoding spatio-temporal context and applying an attention mechanism, SMAUG effectively represents personalized user representations. Moreover, aiming to extensively explore the semantic information in app usage sessions, SMAUG incorporates LLMs to gain deeper insight into user behavior characteristics revealed in sessions, and also exploits a curriculum representation learning approach based on contrastive learning, exploring session characteristics from elementary to profound. Experiments on two real-world datasets show that SMAUG outperforms existing generative baseline approaches by over 25% under the metrics of RMSE, MAE, CRPS, JSD, M-TV, and Spearmanr. The model has also been successfully deployed to assist network service simulation, demonstrating their suitability for downstream tasks in real-world systems.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.