# SEAnet: A Deep Learning Architecture for Data Series Similarity Search

arXiv: https://arxiv.org/abs/2603.01448 · HTML: https://mlsanity.com/paper/2603.01448/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data](https://mlsanity.com/paper/2005.10996/) (2020)
- [Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis](https://mlsanity.com/paper/1806.08946/) (2018)
- [TimeNet: Pre-trained deep recurrent neural network for time series classification](https://mlsanity.com/paper/1706.08838/) (2017)
- [Random Warping Series: A Random Features Method for Time-Series Embedding](https://mlsanity.com/paper/1809.05259/) (2018)
- [Return of the Lernaean Hydra: Experimental Evaluation of Data Series Approximate Similarity Search](https://mlsanity.com/paper/2006.11459/) (2020)
- [Hercules Against Data Series Similarity Search](https://mlsanity.com/paper/2212.13297/) (2022)
- [The Lernaean Hydra of Data Series Similarity Search: An Experimental Evaluation of the State of the Art](https://mlsanity.com/paper/2006.11454/) (2020)
- [Fast Data Series Indexing for In-Memory Data](https://mlsanity.com/paper/2110.07519/) (2021)
- [Dumpy: A Compact and Adaptive Index for Large Data Series Collections](https://mlsanity.com/paper/2304.08264/) (2023)
- [ProS: Data Series Progressive k-NN Similarity Search and Classification with Probabilistic Quality Guarantees](https://mlsanity.com/paper/2212.13310/) (2022)
- [Coconut: sortable summarizations for scalable indexes over static and streaming data series](https://mlsanity.com/paper/2006.11474/) (2020)
- [Coconut: a scalable bottom-up approach for building data series indexes](https://mlsanity.com/paper/2006.13713/) (2020)
- [Scalable Data Series Subsequence Matching with ULISSE](https://mlsanity.com/paper/2009.10373/) (2020)
- [Odyssey: A Journey in the Land of Distributed Data Series Similarity Search](https://mlsanity.com/paper/2301.11049/) (2023)

## Abstract (arXiv)

A key operation for massive data series collection analysis is similarity search. According to recent studies, SAX-based indexes offer state-of-the-art performance for similarity search tasks. However, their performance lags under high-frequency, weakly correlated, excessively noisy, or other dataset-specific properties. In this work, we propose Deep Embedding Approximation (DEA), a novel family of data series summarization techniques based on deep neural networks. Moreover, we describe SEAnet, a novel architecture especially designed for learning DEA, that introduces the Sum of Squares preservation property into the deep network design. We further enhance SEAnet with SEAtrans encoder. Finally, we propose novel sampling strategies, SEAsam and SEAsamE, that allow SEAnet to effectively train on massive datasets. Comprehensive experiments on 7 diverse synthetic and real datasets verify the advantages of DEA learned using SEAnet in providing high-quality data series summarizations and similarity search results.