arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.27992cs.LG
收藏

Patched-DeltaNet: 用于线性时间异常检测的令牌级事件驱动记忆

Patched-DeltaNet: Token-Level Event-Driven Memory for Linear-Time Anomaly Detection

ETRI(电子与电信研究院)

Tae-Gyun Lee, Junyoung Park, Kyu Won Han

AI总结:

提出Patched-DeltaNet架构,结合时间序列分块与门控Delta网络,通过令牌级事件驱动记忆实现线性时间复杂度的异常检测,在SMD基准上达到ROC-AUC 0.957和PA-F1 0.822。

摘要:

时间序列异常检测对于维护关键任务系统的可靠性至关重要。虽然基于Transformer的模型(如PatchTST)表现出色,但其$\mathcal{O}(L^2)$的计算复杂度严重限制了在资源受限环境中的部署。在本文中,我们提出了Patched-DeltaNet,一种结合时间序列分块与门控Delta网络的新型架构。通过整合这些范式,我们假设并证明了令牌级事件驱动记忆的出现,其中分块机制提取局部语义块,而误差驱动的DeltaNet仅在发生显著物理变化(定义为delta)时更新其循环状态。这种协同作用有效滤除背景噪声并捕获突然的异常漂移。我们在服务器机器数据集(SMD)基准上的严格实验证明了Patched-DeltaNet的结构优越性和样本效率。通过在统一评估约束和相同计算预算下严格优于最新架构,我们的模型实现了ROC-AUC 0.957和PA-F1 0.822,同时将计算复杂度大幅降低至理论最小值$\mathcal{O}(L/P)$。

英文摘要:

Time series anomaly detection is critical for maintaining the reliability of mission-critical systems. While Transformer-based models like PatchTST have shown remarkable performance, their $\mathcal{O}(L^2)$ computational complexity severely limits deployment in resource-constrained environments. In this paper, we propose Patched-DeltaNet, a novel architecture combining time-series patching with Gated Delta Networks. By integrating these paradigms, we hypothesize and demonstrate the emergence of token-level event-driven memory, whereby the patching mechanism extracts local semantic chunks, while the error-driven DeltaNet updates its recurrent state exclusively when significant physical changes, defined as deltas, occur. This synergy effectively filters out background noise and captures sudden anomalous drifts. Our rigorous experiments on the Server Machine Dataset (SMD) benchmark demonstrate the structural superiority and sample efficiency of Patched-DeltaNet. By strictly outperforming recent architectures under unified evaluation constraints and identical compute budgets, our model yields an ROC-AUC of 0.957 and PA-F1 of 0.822, while drastically reducing computational complexity to the theoretical minimum of $\mathcal{O}(L/P)$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑