arXiv：cs.LG· SiRui He, Kai Liang Lew, Chui Zi Ong, Chean Khim Toa·· 3 小时前AI 评分33
AIGS：面向非平稳数据流在线表征学习的自适应增量门控系统
AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data Streams
AI 导读
研究者提出自适应增量门控系统 AIGS，一种轻量闭环状态感知适配框架，通过 Shock Ratio 残差反馈驱动连续可塑性控制器，在稳定性与可塑性间平滑插值，每步复杂度为线性 O(k·d)。在 ETTm1 和 ETTm2 数据集上，AIGS 分别实现 8.31 和 9.88 步的预警提前量；在 PMS 交通数据集上突变后恢复更快，在 Weather 数据集上提升异常召回并抑制噪声过拟合。
正文
Abstract:Real-time data streams in Web of Things (WoT) and edge computing environments often evolve through latent regime changes. For online representation learning under strict computational constraints, the central problem is resolving the stability-plasticity dilemma: keeping useful historical knowledge while rapidly reacting to concept drift. Existing methods employ fixed update schedules or rolling windows. However, they suffer from parameter ossification during sudden shifts and waste computational resources when the stream remains stable. This paper proposes the Adaptive Incremental Gating System (AIGS), a lightweight closed-loop state-aware adaptation framework. AIGS introduces the Shock Ratio, an endogenous residual feedback mechanism that normalizes current reconstruction error against recent variation. This signal drives a Continuous Plasticity Controller that smoothly interpolates between learning plasticity and memory retention. By treating representation learning as a closed-loop control mechanism, AIGS avoids catastrophic forgetting and maintains a strictly linear $\mathcal{O}\left(k\cdot d\right)$ per-step complexity suitable for latency-sensitive edge devices. Experiments on real-world smart city dynamic streams-spanning traffic networks, meteorological systems, and industrial infrastructure-demonstrate distinct domain-dependent advantages. On Electricity Transformer Temperature datasets, AIGS achieves preventative early-warning lead times of 8.31 (ETTm1) and 9.88 (ETTm2) steps under gradual degradation. On Performance Measurement System traffic datasets, it shows significantly faster post-shift recovery after abrupt mutations. On the highly noisy Weather dataset, it improves anomaly recall while resisting stochastic noise overfitting. These findings establish AIGS as a practical, plug-and-play adapter for resource-constrained edge monitoring systems.
| Comments: | 11 pages, 6 figures, 8 tables |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02661 [cs.LG] |
| (or arXiv:2610.02661v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02661 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: SiRui He [view email]
[v1]
Fri, 2 Oct 2026 01:29:07 UTC (975 KB)
来源：arXiv：cs.LG · arxiv.org