U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications

TL;DR

U-MASK introduces a novel user-adaptive spatio-temporal masking approach for personalized mobile AI, effectively balancing immediacy, stability, and generalization in data-scarce, non-stationary environments.

Contribution

It models mobile behavior as a spatio-temporal tensor and unifies various personalization tasks through a mask-guided generative framework with user-specific representations.

Findings

Outperforms state-of-the-art methods in short-term and long-term predictions.

Achieves significant improvements under severe data sparsity.

Effective cold-start personalization demonstrated.

Abstract

Personalized mobile artificial intelligence applications are widely deployed, yet they are expected to infer user behavior from sparse and irregular histories under a continuously evolving spatio-temporal context. This setting induces a fundamental tension among three requirements, i.e., immediacy to adapt to recent behavior, stability to resist transient noise, and generalization to support long-horizon prediction and cold-start users. Most existing approaches satisfy at most two of these requirements, resulting in an inherent impossibility triangle in data-scarce, non-stationary personalization. To address this challenge, we model mobile behavior as a partially observed spatio-temporal tensor and unify short-term adaptation, long-horizon forecasting, and cold-start recommendation as a conditional completion problem, where a user- and task-specific mask specifies which coordinates are treated as evidence. We propose U-MASK, a user-adaptive spatio-temporal masking method that allocates evidence budgets based on user reliability and task sensitivity. To enable mask generation under sparse observations, U-MASK learns a compact, task-agnostic user representation from app and location histories via U-SCOPE, which serves as the sole semantic conditioning signal. A shared diffusion transformer then performs mask-guided generative completion while preserving observed evidence, so personalization and task differentiation are governed entirely by the mask and the user representation. Experiments on real-world mobile datasets demonstrate consistent improvements over state-of-the-art methods across short-term prediction, long-horizon forecasting, and cold-start settings, with the largest gains under severe data sparsity. The code and dataset will be available at https://github.com/NICE-HKU/U-MASK.