cs.LGNov 19, 2026

TRCF: Temporal-Reference Complementary Forecasting for Irregular Multivariate Time Series

Authors: Xudong Zuo, Shusen Ma, Qirui Chen, Bing Fan, Yun-Bo Zhao

Organizations: Institute of Advanced Technology, University of Science and Technology of China, Hefei, China · School of Computer Science and Technology, University of Science and Technology of China, Hefei, China · Department of Automation, University of Science and Technology of China, Hefei, China

Abstract

Irregular multivariate time series forecasting supports healthcare monitoring, environmental analysis, and activity recognition. Channel-independent (CI) approaches capture each variable's temporal patterns but do not explicitly use observations from other variables. Channel-dependent (CD) modeling exploits relationships among variables, yet asynchronous measurements make these relationships difficult to learn. Incorporating cross-variable information while preserving each variable's irregular history therefore remains a key challenge. We propose Temporal-Reference Complementary Forecasting (TRCF), a framework that augments a compact CI forecaster with a complementary CD branch. ANCHOR aggregates observed values and timestamps at shared temporal locations, retaining observation support to form compact CI features. BRIDGE constructs complementary features through history completion. It first estimates each variable's historical values from its own observations, then uses differences between other variables' observed and estimated values at nearby times to correct missing entries. The completed history preserves observed values and is encoded to supply context alongside the direct CI representation. Finally, the two representations are fused, combined with the query-time embedding, and passed to a shallow multilayer perceptron for forecasting. Experiments on four real-world datasets show that TRCF achieves the lowest mean squared error and mean absolute error in the main benchmark comparison, while reducing measured peak inference memory by 17.28% to 87.98% relative to APN.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CVTA: Cross-Variable Temporal Attention for Multivariate Irregular Time Series Prediction

    Oct 18, 2026Ankitkumar Joshi, Milos HauskrechtMultivariate Time Series ForecastingTime Series Forecasting

  2. QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting

    Oct 3, 2026Linfeng Wang, Ruitong Zhang, Kai Zhao +6Multivariate Time Series ForecastingIrregular Time-Series Modeling