QuITE: Query-Based Irregular Time Series Embedding
For practitioners working with irregularly sampled time series, QuITE provides a simple, effective way to reuse existing regular MTS models without architectural changes or interpolation.
QuITE is a plug-and-play embedding module for irregular multivariate time series that uses learnable query tokens and a single self-attention layer to produce backbone-compatible latent representations, achieving average relative gains of up to 54.7% in forecasting and 15.8% in classification across diverse datasets and architectures.
Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling. Existing approaches typically either (i) design specialized architectures that limit the reuse of proven Multivariate Time Series (MTS) models, or (ii) map IMTS onto regular temporal grids through interpolation, which may distort temporal dynamics by introducing artificial values. To address these limitations, we propose a new input-embedding-based approach. We identify that the key bottleneck lies not in the backbone architecture, but in conventional embedding layers that assume uniform sampling. In this work, we introduce QuITE (Query-Based Irregular Time Series Embedding), a simple yet effective plug-and-play embedding module for IMTS. QuITE employs learnable query tokens to aggregate irregular observations through a single self-attention layer, directly producing backbone-compatible latent representations without artificial value generation or architectural modification. Extensive experiments on real-world benchmarks show that QuITE consistently improves MTS models, yielding average relative gains of up to $54.7\%$ in forecasting and $15.8\%$ in classification across diverse datasets and backbone architectures. Code is available at: https://github.com/Meaningfull9502/QuITE.