arXiv：cs.LG· Zeyu Shi, Yanhui Luo, Ziming Hong, Chongyang Gao, Kezhen Chen, Shanshan Ye, Lixu Wang·· 3 小时前AI 评分34
RDTU：面向时间序列预测的残差扩散机器遗忘框架
On Unlearning for Time-series Forecasting
AI 导读
针对时间序列预测中删除敏感或损坏数据的需求，研究者提出机器遗忘框架 RDTU，用残差扩散生成反事实预测的伪标签场来指导轻量模型更新。该方法先用保留集神经正切核预测器得到与删除兼容的基础预测，再量化受影响窗口的全局与局部结构支持度。实验显示 RDTU 产出的遗忘模型与完全重训练的结果最为接近。
正文
Abstract:Time-series forecasting is widely used in sensitive domains. Models in these settings are often trained on longitudinal user- or entity-level records, which may later require removal because they contain sensitive or proprietary information or have been corrupted by sensor failures. To address such deletion requests without costly retraining, machine unlearning has been widely studied as a practical mechanism for privacy protection and data governance. However, the application of machine unlearning to time series prediction has not yet been well realized; this is mainly due to the following unique challenges: Gradient-based unlearning can be unstable because a deleted observation participates in multiple causally connected forecasting windows, causing parameter updates to propagate beyond the requested interval and degrade retained forecasting utility. Label-guided updating offers a more controlled alternative, but continuous and context-dependent forecasts lack a suitable replacement target, while the exact-retrained output is unavailable during unlearning. Moreover, the remaining support for a deleted temporal pattern is highly non-uniform. Some affected windows retain structurally similar counterparts in the retained data, whereas others become underrepresented or isolated. We present RDTU, a Residual Diffusion framework for time-series unlearning. RDTU first uses a retained-set neural tangent kernel predictor to obtain a deletion-compatible base forecast. Then it quantifies the global and local structural support of each affected window using the volume contribution of the retained-reference data. Then a diffusion model generates a residual correction that estimates the counterfactual forecast, yielding a pseudo-label field that guides a lightweight model update. Experiments show that RDTU consistently produces unlearned models that most closely match exact retraining.
| Comments: | 22 pages |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02865 [cs.LG] |
| (or arXiv:2610.02865v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02865 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lixu Wang [view email]
[v1]
Fri, 2 Oct 2026 06:03:44 UTC (909 KB)
来源：arXiv：cs.LG · arxiv.org