# PSEUDo: Interactive Pattern Search in Multivariate Time Series with Locality-Sensitive Hashing and Relevance Feedback

arXiv: https://arxiv.org/abs/2104.14962 · HTML: https://mlsanity.com/paper/2104.14962/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 125 references that are in the map.
- First posted on arXiv 30 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers](https://mlsanity.com/paper/1801.06889/) (2018)
- [explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning](https://mlsanity.com/paper/1908.00087/) (2019)
- [CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization](https://mlsanity.com/paper/2004.15004/) (2020)
- [Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series](https://mlsanity.com/paper/1809.04758/) (2018)
- [Open Source Software for Efficient and Transparent Reviews](https://mlsanity.com/paper/2006.12166/) (2020)
- [The State of the Art in Integrating Machine Learning into Visual Analytics](https://mlsanity.com/paper/1802.07954/) (2018)
- [Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach](https://mlsanity.com/paper/1808.00703/) (2018)
- [NeuralWarp: Time-Series Similarity with Warping Networks](https://mlsanity.com/paper/1812.08306/) (2018)
- [SAX Navigator: Time Series Exploration through Hierarchical Clustering](https://mlsanity.com/paper/1908.05505/) (2019)
- [Modeling Time Series Similarity with Siamese Recurrent Networks](https://mlsanity.com/paper/1603.04713/) (2016)
- [SSH (Sketch, Shingle, & Hash) for Indexing Massive-Scale Time Series](https://mlsanity.com/paper/1610.07328/) (2016)
- [A General Framework for Density Based Time Series Clustering Exploiting a Novel Admissible Pruning Strategy](https://mlsanity.com/paper/1612.00637/) (2016)
- [You can't always sketch what you want: Understanding Sensemaking in Visual Query Systems](https://mlsanity.com/paper/1710.00763/) (2017)
- [ShapeSearch: A Flexible and Efficient System for Shape-based Exploration of Trendlines](https://mlsanity.com/paper/1811.07977/) (2018)
- [FDive: Learning Relevance Models using Pattern-based Similarity Measures](https://mlsanity.com/paper/1907.12489/) (2019)
- [Twin Subsequence Search in Time Series](https://mlsanity.com/paper/2104.06874/) (2021)

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

- [Boosting Diffusion Models with an Adaptive Momentum Sampler](https://mlsanity.com/paper/2308.11941/) (2023)
- [DeepVATS: Deep Visual Analytics for Time Series](https://mlsanity.com/paper/2302.03858/) (2023)

## Abstract (arXiv)

We present PSEUDo, an adaptive feature learning technique for exploring visual patterns in multi-track sequential data. Our approach is designed with the primary focus to overcome the uneconomic retraining requirements and inflexible representation learning in current deep learning-based systems. Multi-track time series data are generated on an unprecedented scale due to increased sensors and data storage. These datasets hold valuable patterns, like in neuromarketing, where researchers try to link patterns in multivariate sequential data from physiological sensors to the purchase behavior of products and services. But a lack of ground truth and high variance make automatic pattern detection unreliable. Our advancements are based on a novel query-aware locality-sensitive hashing technique to create a feature-based representation of multivariate time series windows. Most importantly, our algorithm features sub-linear training and inference time. We can even accomplish both the modeling and comparison of 10,000 different 64-track time series, each with 100 time steps (a typical EEG dataset) under 0.8 seconds. This performance gain allows for a rapid relevance feedback-driven adaption of the underlying pattern similarity model and enables the user to modify the speed-vs-accuracy trade-off gradually. We demonstrate superiority of PSEUDo in terms of efficiency, accuracy, and steerability through a quantitative performance comparison and a qualitative visual quality comparison to the state-of-the-art algorithms in the field. Moreover, we showcase the usability of PSEUDo through a case study demonstrating our visual pattern retrieval concepts in a large meteorological dataset. We find that our adaptive models can accurately capture the user's notion of similarity and allow for an understandable exploratory visual pattern retrieval in large multivariate time series datasets.