用图像化扩散模型生成更真实多样的手机使用数据，解决稀疏和不均衡难题。
MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion
- 将稀疏的多变量使用序列转为相关性图像，再用带三重注意力的U-Net生成
- 生成数据在判别准确率上达0.1526，优于最强基线（0.3476）
- 适合隐私敏感场景下的用户行为模拟与推荐系统训练
手机使用轨迹对用户行为预测和应用推荐至关重要，但受隐私限制和大规模数据收集成本制约。尽管生成模型在一般时间序列上表现良好，应用于手机使用数据仍面临三大挑战：(i) 用户活动有限导致数据严重稀疏，(ii) 变量类型异质性增加联合建模难度，(iii) 不同应用间功能差异造成使用模式显著不均衡。为此，我们提出多变量图像扩散模型（MIDiff），其在由交叉格拉姆角和场（C-GASF）定义的图像空间中运行。C-GASF将稀疏的多变量序列转换为相关性图像，MIDiff则通过带三重注意力的U-Net结构保持时序一致性与变量依赖关系。实验表明，MIDiff在保真度指标上达到当前最优水平，判别准确率（DA）为0.1526，显著优于最强基线模型ZITS-VAE的0.3476，验证了其生成真实且多样手机使用轨迹的有效性。代码已开源：https://github.com/YilaiLiu-HKU/MIDiff。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。