# Series2Graph: Graph-based Subsequence Anomaly Detection for Time Series

arXiv: https://arxiv.org/abs/2207.12208 · HTML: https://mlsanity.com/paper/2207.12208/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 62 references that are in the map.
- First posted on arXiv 25 Jul 2022.

## Builds on (most cited first, 7 of 7)

- [Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network](https://mlsanity.com/paper/1703.09752/) (2017)
- [Matrix Profile Goes MAD: Variable-Length Motif And Discord Discovery in Data Series](https://mlsanity.com/paper/2008.13447/) (2020)
- [Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection](https://mlsanity.com/paper/1801.03168/) (2018)
- [Return of the Lernaean Hydra: Experimental Evaluation of Data Series Approximate Similarity Search](https://mlsanity.com/paper/2006.11459/) (2020)
- [The Lernaean Hydra of Data Series Similarity Search: An Experimental Evaluation of the State of the Art](https://mlsanity.com/paper/2006.11454/) (2020)
- [ParIS+: Data Series Indexing on Multi-Core Architectures](https://mlsanity.com/paper/2009.00166/) (2020)
- [MESSI: In-Memory Data Series Indexing](https://mlsanity.com/paper/2009.00786/) (2020)

## Built on by (most cited first, 13 of 13)

- [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2306.10347/) (2023)
- [TAB: Unified Benchmarking of Time Series Anomaly Detection Methods](https://mlsanity.com/paper/2506.18046/) (2025)
- [LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version](https://mlsanity.com/paper/2302.12721/) (2023)
- [VUS: Effective and Efficient Accuracy Measures for Time-Series Anomaly Detection](https://mlsanity.com/paper/2502.13318/) (2025)
- [Anomaly Prediction: A Novel Approach with Explicit Delay and Horizon](https://mlsanity.com/paper/2408.04377/) (2024)
- [SoftED: Metrics for Soft Evaluation of Time Series Event Detection](https://mlsanity.com/paper/2304.00439/) (2023)
- [MSAD: A Deep Dive into Model Selection for Time series Anomaly Detection](https://mlsanity.com/paper/2510.26643/) (2025)
- [Graphint: Graph-based Time Series Clustering Visualisation Tool](https://mlsanity.com/paper/2503.07698/) (2025)
- [DIM-SUM: Dynamic IMputation for Smart Utility Management](https://mlsanity.com/paper/2506.20023/) (2025)
- [Causal Graph Profiling via Structural Divergence for Robust Anomaly Detection in Cyber-Physical Systems](https://mlsanity.com/paper/2508.09504/) (2025)
- [Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection](https://mlsanity.com/paper/2605.26193/) (2026)
- [In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in Streams](https://mlsanity.com/paper/2609.39215/) (2026)
- [From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring](https://mlsanity.com/paper/2609.39257/) (2026)

## Abstract (arXiv)

Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains. However, the approaches proposed so far in the literature have severe limitations: they either require prior domain knowledge used to design the anomaly discovery algorithms, or become cumbersome and expensive to use in situations with recurrent anomalies of the same type. In this work, we address these problems, and propose an unsupervised method suitable for domain agnostic subsequence anomaly detection. Our method, Series2Graph, is based on a graph representation of a novel low-dimensionality embedding of subsequences. Series2Graph needs neither labeled instances (like supervised techniques) nor anomaly-free data (like zero-positive learning techniques), and identifies anomalies of varying lengths. The experimental results, on the largest set of synthetic and real datasets used to date, demonstrate that the proposed approach correctly identifies single and recurrent anomalies without any prior knowledge of their characteristics, outperforming by a large margin several competing approaches in accuracy, while being up to orders of magnitude faster. This paper has appeared in VLDB 2020.