# WATCH: Wasserstein Change Point Detection for High-Dimensional Time Series Data

arXiv: https://arxiv.org/abs/2201.07125 · HTML: https://mlsanity.com/paper/2201.07125/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 54 references that are in the map.
- First posted on arXiv 18 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [An Evaluation of Change Point Detection Algorithms](https://mlsanity.com/paper/2003.06222/) (2020)
- [A Nonparametric Approach for Multiple Change Point Analysis of Multivariate Data](https://mlsanity.com/paper/1306.4933/) (2013)
- [Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with β-Divergences](https://mlsanity.com/paper/1806.02261/) (2018)
- [Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection](https://mlsanity.com/paper/1805.05383/) (2018)
- [Multivariate goodness-of-Fit tests based on Wasserstein distance](https://mlsanity.com/paper/2003.06684/) (2020)
- [Changepoint Detection in the Presence of Outliers](https://mlsanity.com/paper/1609.07363/) (2016)
- [Learning disentangled representations with the Wasserstein Autoencoder](https://mlsanity.com/paper/2010.03459/) (2020)

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

- [A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems](https://mlsanity.com/paper/2301.07799/) (2023)
- [Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2](https://mlsanity.com/paper/2208.05056/) (2022)
- [Maximum Mean Discrepancy on Exponential Windows for Online Change Detection](https://mlsanity.com/paper/2205.12706/) (2022)
- [Adaptive Bernstein Change Detector for High-Dimensional Data Streams](https://mlsanity.com/paper/2306.12974/) (2023)
- [System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games](https://mlsanity.com/paper/2212.04603/) (2022)
- [A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism](https://mlsanity.com/paper/2309.03720/) (2023)
- [Neural Stochastic Differential Equations with Change Points: A Generative Adversarial Approach](https://mlsanity.com/paper/2312.13152/) (2023)
- [Estimating Environmental Cost Throughout Model's Adaptive Life Cycle](https://mlsanity.com/paper/2408.01446/) (2024)
- [A Self-Organizing Clustering System for Unsupervised Distribution Shift Detection](https://mlsanity.com/paper/2404.16656/) (2024)
- [Unsupervised Assessment of Landscape Shifts Based on Persistent Entropy and Topological Preservation](https://mlsanity.com/paper/2410.04183/) (2024)
- [WWAggr: A Window Wasserstein-based Aggregation for Ensemble Change Point Detection](https://mlsanity.com/paper/2506.08066/) (2025)
- [Machine Failure Detection Based on Projected Quantum Models](https://mlsanity.com/paper/2601.15641/) (2026)
- [High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability](https://mlsanity.com/paper/2609.24278/) (2026)

## Abstract (arXiv)

Detecting relevant changes in dynamic time series data in a timely manner is crucially important for many data analysis tasks in real-world settings. Change point detection methods have the ability to discover changes in an unsupervised fashion, which represents a desirable property in the analysis of unbounded and unlabeled data streams. However, one limitation of most of the existing approaches is represented by their limited ability to handle multivariate and high-dimensional data, which is frequently observed in modern applications such as traffic flow prediction, human activity recognition, and smart grids monitoring. In this paper, we attempt to fill this gap by proposing WATCH, a novel Wasserstein distance-based change point detection approach that models an initial distribution and monitors its behavior while processing new data points, providing accurate and robust detection of change points in dynamic high-dimensional data. An extensive experimental evaluation involving a large number of benchmark datasets shows that WATCH is capable of accurately identifying change points and outperforming state-of-the-art methods.