# Unveiling the Flaws: A Critical Analysis of Initialization Effect on Time Series Anomaly Detection

arXiv: https://arxiv.org/abs/2408.06620 · HTML: https://mlsanity.com/paper/2408.06620/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## Builds on (most cited first, 10 of 10)

- [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2106.06947/) (2021)
- [Multivariate Time-series Anomaly Detection via Graph Attention Network](https://mlsanity.com/paper/2009.02040/) (2020)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [Towards a Rigorous Evaluation of Time-series Anomaly Detection](https://mlsanity.com/paper/2109.05257/) (2021)
- [An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series](https://mlsanity.com/paper/2109.11428/) (2021)
- [Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis](https://mlsanity.com/paper/2208.07448/) (2022)
- [Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook](https://mlsanity.com/paper/2205.05173/) (2022)
- [DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection](https://mlsanity.com/paper/2106.05410/) (2021)
- [C3: Cross-instance guided Contrastive Clustering](https://mlsanity.com/paper/2211.07136/) (2022)
- [Open-Set Multivariate Time-Series Anomaly Detection](https://mlsanity.com/paper/2310.12294/) (2023)

## Built on by (most cited first, 2 of 2)

- [Exploring Pose-Based Anomaly Detection for Retail Security: A Real-World Shoplifting Dataset and Benchmark](https://mlsanity.com/paper/2501.06591/) (2025)
- [Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning](https://mlsanity.com/paper/2607.00720/) (2026)

## Abstract (arXiv)

Deep learning for time-series anomaly detection (TSAD) has gained significant attention over the past decade. Despite the reported improvements in several papers, the practical application of these models remains limited. Recent studies have cast doubt on these models, attributing their results to flawed evaluation techniques. However, the impact of initialization has largely been overlooked. This paper provides a critical analysis of the initialization effects on TSAD model performance. Our extensive experiments reveal that TSAD models are highly sensitive to hyperparameters such as window size, seed number, and normalization. This sensitivity often leads to significant variability in performance, which can be exploited to artificially inflate the reported efficacy of these models. We demonstrate that even minor changes in initialization parameters can result in performance variations that overshadow the claimed improvements from novel model architectures. Our findings highlight the need for rigorous evaluation protocols and transparent reporting of preprocessing steps to ensure the reliability and fairness of anomaly detection methods. This paper calls for a more cautious interpretation of TSAD advancements and encourages the development of more robust and transparent evaluation practices to advance the field and its practical applications.