基于图注意力的无监督异常检测模型，提升移动网络数据异常识别精度。
Context-Aware Graph Attention for Unsupervised Telco Anomaly Detection
- 结合图注意力与轻量上下文嵌入，构建无监督异常检测框架。
- 在公开数据集上事件级和点级F1均优于现有方法，误报率显著降低。
- 已部署于国家级运营商核心网，具备工业级鲁棒性，适合电信领域应用。
我们提出C-MTAD-GAT，一种用于移动网络多变量时间序列的无监督、上下文感知图注意力异常检测模型。该模型融合图注意力机制与轻量上下文嵌入，采用确定性重构头和多步预测器生成异常分数。检测阈值通过验证残差自动校准，无需标签，保持全流程无监督。在公开的TELCO数据集上，C-MTAD-GAT在事件级和点级F1指标上持续优于MTAD-GAT和专用于电信的DC-VAE两个前沿基线模型，同时触发的告警数量大幅减少。该模型已在某国家级移动运营商的核心网络中实际部署，验证了其在真实工业环境中的稳健性。
原文摘要 · Abstract (English)
We propose C-MTAD-GAT, an \emph{unsupervised}, \emph{context-aware} graph-attention model for anomaly detection in multivariate time series from mobile networks. C-MTAD-GAT combines graph attention with lightweight context embeddings, and uses a deterministic reconstruction head and multi-step forecaster to produce anomaly scores. Detection thresholds are calibrated \emph{without labels} from validation residuals, keeping the pipeline fully unsupervised. On the public TELCO dataset, C-MTAD-GAT consistently outperforms MTAD-GAT and the Telco-specific DC-VAE, two state-of-the-art baselines, in both event-level and pointwise F1, while triggering substantially fewer alarms. C-MTAD-GAT is also deployed in the Core network of a national mobile operator, demonstrating its resilience in real industrial settings.
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。