Skip to content

Query-Based Irregular Time Series Embedding

Home / Concepts / Query-Based Irregular Time Series Embedding

Query-Based Irregular Time Series Embedding

Auto-generated stub. Edit this file to add more details.

A plug-and-play embedding module for irregular multivariate time series that uses learnable query tokens and self-attention to generate backbone-compatible latent representations.

Why It Matters

It provides a model-agnostic mechanism to convert irregular time series into regular latent representations, overcoming the typical reliance on interpolation or specialized architectures.

Evidence

QuITE (Query-Based Irregular Time Series Embedding), a simple yet effective plug-and-play embedding module for IMTS.

Metadata & Links

created_at
2026-05-30T06:07:58Z