# Latent Structural Similarity Networks for Unsupervised Discovery in Multivariate Time Series

arXiv: https://arxiv.org/abs/2601.18803 · HTML: https://mlsanity.com/paper/2601.18803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 7 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 3 of 3)

- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)

## Abstract (arXiv)

This paper proposes a task-agnostic discovery layer for multivariate time series that constructs a relational hypothesis graph over entities without assuming linearity, stationarity, or a downstream objective. The method learns window-level sequence representations using an unsupervised sequence-to-sequence autoencoder, aggregates these representations into entity-level embeddings, and induces a sparse similarity network by thresholding a latent-space similarity measure. This network is intended as an analyzable abstraction that compresses the pairwise search space and exposes candidate relationships for further investigation, rather than as a model optimized for prediction, trading, or any decision rule. The framework is demonstrated on a challenging real-world dataset of hourly cryptocurrency returns, illustrating how latent similarity induces coherent network structure; a classical econometric relation is also reported as an external diagnostic lens to contextualize discovered edges.