- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper proposes EDSR, a causality-guided framework for zero-shot multivariate time-series anomaly detection under extreme domain shifts. The main idea is to leverage causal relationships that are assumed to remain stable when the magnitude of the input signals changes significantly. The framework consists of six training phases, including causal discovery, causality-aware contrastive learning, spatio-temporal attention refinement, adversarial representation learning, memory-based screening, and domain adaptation. During inference, it adopts an edge-cloud architecture and combines multiple anomaly scores for detection and root-cause attribution. Experiments on two synthetic datasets, VAR-100 and Lorenz-96, show that EDSR achieves better detection performance than the selected baselines under 100× magnitude shifts.
Critical strengths
-
The paper addresses a practically relevant problem, as time-series anomaly detectors may encounter substantial distribution shifts between training and deployment. Exploring structural relationships that may remain stable across operating conditions is a potentially interesting direction.
-
The proposed framework also considers deployment efficiency through an edge-cloud architecture, aiming to reduce computational overhead by filtering normal samples before more expensive anomaly detection.
Critical weaknesses
-
The paper argues that normalization may destroy useful information under extreme domain shifts. However, it is unclear what information would be lost, especially when the shift is simply a 100× magnitude scaling. This claim needs further justification.
-
The proposed framework is overly complex, involving six training phases. The necessity of each component is not clearly justified, and the ablation studies are insufficient to support the overall design.
-
The final anomaly score combines five weighted scores. Although the weights are selected through grid search, their sensitivity and the contribution of each score are not adequately investigated.
-
The experiments are limited to two synthetic datasets. Evaluation on real-world benchmarks, such as SMD, SWaT, and PSM, would help demonstrate the practical effectiveness of the proposed method.
Questions for authors
See weaknesses.