Latent Structural Similarity Networks for Unsupervised Discovery in Multivariate Time Series
This provides a task-agnostic tool for exploratory analysis in domains like finance, though it is incremental as it builds on unsupervised representation learning without optimizing for predictive tasks.
The paper tackles the problem of discovering relationships in multivariate time series without prior assumptions or a specific task, proposing a method that constructs a sparse similarity network from latent embeddings, and demonstrates it on cryptocurrency returns data, showing coherent network structure and validating edges with an econometric relation.
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.