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

arXiv: https://arxiv.org/abs/2607.14249 · HTML: https://mlsanity.com/paper/2607.14249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 54 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2402.19072/) (2024)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Causal Recurrent Variational Autoencoder for Medical Time Series Generation](https://mlsanity.com/paper/2301.06574/) (2023)
- [Generative Adversarial Networks](https://mlsanity.com/paper/1406.2661/) (2014)
- [Temporal Query Network for Efficient Multivariate Time Series Forecasting](https://mlsanity.com/paper/2505.12917/) (2025)
- [TSGBench: Time Series Generation Benchmark](https://mlsanity.com/paper/2309.03755/) (2023)
- [NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging](https://mlsanity.com/paper/2310.04429/) (2023)
- [Population Aware Diffusion for Time Series Generation](https://mlsanity.com/paper/2501.00910/) (2025)
- [Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts](https://mlsanity.com/paper/2507.07100/) (2025)
- [TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data](https://mlsanity.com/paper/2406.16028/) (2024)
- [AppGen: Mobility-aware App Usage Behavior Generation for Mobile Users](https://mlsanity.com/paper/2412.07267/) (2024)
- [Real World Longitudinal iOS App Usage Study at Scale](https://mlsanity.com/paper/1912.12526/) (2019)
- [MTLComb: multi-task learning combining regression and classification tasks for joint feature selection](https://mlsanity.com/paper/2405.09886/) (2024)
- [LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic Prediction](https://mlsanity.com/paper/2507.17795/) (2025)

## Abstract (arXiv)

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.