MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion

Researchers propose MIDiff, a diffusion-based framework that transforms sparse multivariate mobile usage sequences into correlation images using Cross-Gramian Angular Sum Field (C-GASF) and employs Triple Attention in a U-Net to generate realistic traces. MIDiff achieves state-of-the-art fidelity, with a Discriminative Accuracy of 0.1526 versus 0.3476 for the strongest baseline, addressing sparsity, heterogeneity, and imbalance in mobile usage data.

arXiv:2607.14249v1 Announce Type: new Abstract: Mobile usage traces are critical for tasks such as user behavior prediction and app recommendation, yet their use is constrained by privacy restrictions and costly large-scale data collection. Although generative models perform well on general time series, their application to mobile usage data remains challenging because i limited user activity causes severe sparsity, ii heterogeneous variable types complicate joint modeling, and iii functional differences across apps create pronounced usage imbalance. To address these challenges, we propose Multivariate-Imaging Diffusion MIDiff , a diffusion-based framework operating in an imaging space defined by Cross-Gramian Angular Sum Field C-GASF . C-GASF transforms sparse multivariate sequences into correlation images, while MIDiff employs Triple Attention in a U-Net to preserve temporal consistency and variable dependencies. Experiments show that MIDiff achieves state-of-the-art performance across fidelity metrics. In particular, it obtains a Discriminative Accuracy DA of 0.1526, compared with 0.3476 for the strongest baseline, ZITS-VAE, demonstrating its effectiveness in generating realistic and diverse mobile usage traces. Our code is available at https://github.com/YilaiLiu-HKU/MIDiff.