PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection
2026-06-08 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors found that current methods for spotting unusual patterns in time-series data often ignore how big or small signal changes are, which can miss important clues. To fix this, they created a new scoring method called PAI that checks if size information is being captured and adds new calculations to include it when scoring anomalies. Testing on two datasets, their approach improved all existing methods and helped the best one do even better. Their work highlights that keeping track of amplitude details is important for detecting anomalies in time-series data.
time-series anomaly detectionrepresentation learningamplitude informationcosine similarityEuclidean distanceanomaly scoringpoint-wise medianMAD deviationmean-shiftTS2Vec
Authors
Kang Zhang, Wei Jian Lau, Shoushou Ren, Dong Lin, Joon Son Chung, Chuanhao Sun
Abstract
Representation-based time-series anomaly detection algorithms significantly outperform other methods on diverse anomaly detection tasks. However, we notice that they suffer from a major limitation in our evaluation - their learned embeddings are often amplitude-agnostic. Losing amplitude information can degrade performance on amplitude related anomalies, and this failure is prevalent across all existing representation-based methods. To address aforementioned issues, we propose a new anomaly scoring scheme named PAI. PAI consists of two complementary modules, a diagnostic module and a final score augmentation function. The diagnostic module compares cosine and Euclidean scoring on the same representation bank to test whether amplitude information is already captured in the learned representation. Then in final score augmentation function, PAI computes a point-wise median and MAD deviation score and a local mean-shift score-which are fused with the representation score to produce the final anomaly score. On the TSB-AD-U-Eva and TAB UV datasets, PAI improves all four evaluated representation-based methods across every reported metric, achieving average VUS-PR gains of 98.4% and 36.8%, respectively. Among all evaluated combinations, PaAno + PAI achieves the best performance, outperforming the state-of-the-art method by 15%. Further evaluation on bootstrap confidence intervals, anomaly-type breakdowns, and a TS2Vec input-normalization ablation further support the proposed scheme. These results suggest that explicitly retaining amplitude information is important for representation-based time-series anomaly detection, which has been underemphasized in existing scoring schemes. Code is available at: https://github.com/pantheon5100/PAI