arXiv：cs.LG· Xudong Mou, Tiejun Wang, Rui Wang, Hui Wang, Pin Liu, Tianyu Wo, Xudong Liu, Renyu Yang·· 4 小时前AI 评分34
MORA：面向漂移鲁棒的时间序列异常检测，建模观测变化
MORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection
AI 导读
研究者提出 MORA，一个漂移鲁棒的时间序列异常检测框架，通过配对短期与长期视角重建同一局部目标，用重建差距衡量上下文对局部偏差的支持度。该机制采用数据依赖的校正方式保守调整主异常分数，上下文仅在能改善同一目标重建时才降低分数，且无需漂移标注或在线自适应。在四个 TSAD 基准上，MORA 对非平稳性表现出强鲁棒性，同时保持对真实异常的敏感性。
正文
Abstract:Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift and true anomalies can cause similar local changes, making it difficult to tell whether a deviation reflects abnormality or evolving context. Existing methods typically adapt to detected shifts or learn drift-insensitive representations, but do not resolve this ambiguity. We define this problem as \emph{temporal change disambiguation}: determining whether a local deviation is explained by broader temporal evolution. We introduce MORA, a drift-robust TSAD framework that reconstructs the same local target from paired short- and long-term views. The reconstruction gap measures contextual support for a local deviation, and a data-dependent correction mechanism conservatively adjusts the primary local anomaly score. Context can only reduce the score when it improves reconstruction of the same target. MORA needs neither drift annotations nor online adaptation. Experiments on four TSAD benchmarks show strong robustness to non-stationarity while preserving sensitivity to genuine anomalies.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.09473 [cs.LG] |
| (or arXiv:2610.09473v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09473 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xudong Mou [view email]
[v1]
Wed, 7 Oct 2026 05:31:22 UTC (730 KB)
来源：arXiv：cs.LG · arxiv.org