Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection

arXiv:2603.12916 · cs.LG, cs.AI · Submitted 2026-03-13 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-03-13

Updated: 2026-09-12

Comments: This manuscript has been accepted for publication at ECML-PKDD 2026. The final version will be published in the conference proceedings. Main: 17 Pages, 7 Figures, 3 Tables; Appendix: 3 Pages, 4 Tables

Journal ref: Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track, Demo Track and Industrial Track, ECML PKDD 2026, Lecture Notes in Computer Science, vol. 16950, pp. 217-234, Springer, Cham, 2027

DOI: 10.1007/978-3-032-37685-5_13

Code: https://github.com/iis-esslingen/AxonAD

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AUC — 35× in this paper · explained in 2 episodes
• Reconstruction Error — 10× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Benchmark — 8× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Steering — 5× in this paper · explained in 2 episodes
• Self-Supervised Learning — 3× in this paper · explained in 8 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Copula — 2× in this paper · explained in 2 episodes
• Exponential Moving Average (EMA) — 2× in this paper · explained in 2 episodes
• Positional Bias — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attention Entropy — 1× in this paper · explained in 2 episodes
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• International Conference on Machine Learning and Applications — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Time Series Forecasting — 1× in this paper · explained in 3 episodes

Sources

• Competition and Attraction Improve Model Fusion
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
• Bootstrap your own latent: A new approach to self-supervised Learning
• Temporal Convolutional Networks for Action Segmentation and Detection
• COPOD: Copula-Based Outlier Detection
• Decoupled Weight Decay Regularization
• TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
• Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications
• Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
• FITS: Modeling Time Series with $10k$ Parameters
• One Fits All:Power General Time Series Analysis by Pretrained LM

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks