Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting

2026-05-24

AI Summary

Existing retrieval-augmented time series forecasting methods fail to distinguish between invariant structures and dynamic variations within sequences, leading to limited performance in trend-dominated or distribution-shift scenarios. This work proposes a retrieval-guided invariant–dynamic decomposition framework that, for the first time, leverages retrieved sequences as implicit environmental samples. Through attention-based aggregation and a routing mechanism, the model disentangles representations into invariant and dynamic components, which are separately predicted and subsequently fused. The approach enables invariant learning without requiring explicit environment labels and is theoretically shown to reduce variance and approximate invariant representations via retrieval aggregation. Experiments demonstrate that the proposed framework significantly outperforms current foundation models and retrieval baselines in zero-shot settings, substantially improving prediction accuracy and robustness under distribution shifts.

Abstract

Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction. However, our empirical analysis reveals a non-trivial limitation of retrieval-based forecasting: retrieval tends to induce more oscillatory predictions, improving performance on highly fluctuating series while degrading accuracy on smoother, trend-dominated ones. This suggests that retrieved information may be fused into prediction without explicitly distinguishing stable temporal structure from instance-specific variations, which can reduce robustness under distribution shifts. We propose a Retrieval-guided Invariant-Dynamic DEcomposition framework for time series forecasting. Rather than using retrieval as auxiliary predictive context, we leverage retrieved sequences as implicit samples from related environments to guide representation decomposition. Specifically, we first construct a retrieval-aware representation via attention-based aggregation, and then introduce a retrieval-guided routing mechanism to decompose it into an invariant component capturing stable shared structure and a dynamic component modeling context-dependent variations. These two components are forecast separately and fused for final prediction, enabling the model to preserve transferable patterns while remaining adaptive to evolving dynamics. We further design training objectives that encourage invariant learning and disentanglement, and provide theoretical insight showing that retrieval aggregation reduces variance and approximates invariant representation learning without explicit environment supervision. Extensive experiments demonstrate that our method consistently improves robustness under distribution shifts and outperforms existing TSFMs and retrieval-based baselines in zero-shot forecasting settings.

Problem

• time series forecasting
• retrieval-based forecasting
• invariant representation
• distribution shift
• representation decomposition

Innovation

• invariant-dynamic decomposition
• retrieval-guided forecasting
• time series foundation models
• representation disentanglement
• zero-shot forecasting