# E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series

arXiv: https://arxiv.org/abs/2402.14041 · HTML: https://mlsanity.com/paper/2402.14041/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification](https://mlsanity.com/paper/2012.08791/) (2020)
- [Boosting Contrastive Self-Supervised Learning with False Negative Cancellation](https://mlsanity.com/paper/2011.11765/) (2020)
- [Putting An End to End-to-End: Gradient-Isolated Learning of Representations](https://mlsanity.com/paper/1905.11786/) (2019)
- [Toward Supervised Anomaly Detection](https://mlsanity.com/paper/1401.6424/) (2014)
- [RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series](https://mlsanity.com/paper/1812.01767/) (2018)
- [Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data](https://mlsanity.com/paper/1706.03161/) (2017)
- [Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data](https://mlsanity.com/paper/2009.06847/) (2020)
- [STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks](https://mlsanity.com/paper/1902.07849/) (2019)
- [ClaSP -- Parameter-free Time Series Segmentation](https://mlsanity.com/paper/2207.13987/) (2022)
- [LightCTS: A Lightweight Framework for Correlated Time Series Forecasting](https://mlsanity.com/paper/2302.11974/) (2023)
- [Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning](https://mlsanity.com/paper/2104.11952/) (2021)
- [Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes](https://mlsanity.com/paper/2111.07089/) (2021)
- [LiteHAR: Lightweight Human Activity Recognition from WiFi Signals with Random Convolution Kernels](https://mlsanity.com/paper/2201.09310/) (2022)

## Built on by (most cited first, 7 of 7)

- [Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain](https://mlsanity.com/paper/2503.09712/) (2025)
- [CLaP -- State Detection from Time Series](https://mlsanity.com/paper/2504.01783/) (2025)
- [PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentation](https://mlsanity.com/paper/2506.11170/) (2025)
- [Toward Interpretable Evaluation Measures for Time Series Segmentation](https://mlsanity.com/paper/2510.23261/) (2025)
- [Deep Distance Measurement Method for Unsupervised Multivariate Time Series Similarity Retrieval](https://mlsanity.com/paper/2603.12544/) (2026)
- [Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments](https://mlsanity.com/paper/2607.23503/) (2026)
- [Rondo: Unsupervised Discovery of Recurring Temporal Structure](https://mlsanity.com/paper/2609.32500/) (2026)

## Abstract (arXiv)

Cyber-physical system sensors emit multivariate time series (MTS) that monitor physical system processes. Such time series generally capture unknown numbers of states, each with a different duration, that correspond to specific conditions, e.g., "walking" or "running" in human-activity monitoring. Unsupervised identification of such states facilitates storage and processing in subsequent data analyses, as well as enhances result interpretability. Existing state-detection proposals face three challenges. First, they introduce substantial computational overhead, rendering them impractical in resourceconstrained or streaming settings. Second, although state-of-the-art (SOTA) proposals employ contrastive learning for representation, insufficient attention to false negatives hampers model convergence and accuracy. Third, SOTA proposals predominantly only emphasize offline non-streaming deployment, we highlight an urgent need to optimize online streaming scenarios. We propose E2Usd that enables efficient-yet-accurate unsupervised MTS state detection. E2Usd exploits a Fast Fourier Transform-based Time Series Compressor (fftCompress) and a Decomposed Dual-view Embedding Module (ddEM) that together encode input MTSs at low computational overhead. Additionally, we propose a False Negative Cancellation Contrastive Learning method (fnccLearning) to counteract the effects of false negatives and to achieve more cluster-friendly embedding spaces. To reduce computational overhead further in streaming settings, we introduce Adaptive Threshold Detection (adaTD). Comprehensive experiments with six baselines and six datasets offer evidence that E2Usd is capable of SOTA accuracy at significantly reduced computational overhead.