Shiqiao Zhou

Shiqiao Zhou, Holger Schöner, Zipeng Wu et al.

Time series forecasting relies on historical patterns, but real-world series often exhibit non-stationarity and regime shifts that challenge fully parametric forecasters. Inspired by Retrieval-Augmented Generation (RAG), recent work augments forecasters by retrieving relevant historical segments and using them as external evidence at inference time. However, due to the intrinsic non-stationarity of real-world time series, a highly similar past segment does not necessarily imply a similar future, rendering similarity-only retrieval brittle and prone to redundancy. We propose Stationarity-Aware Retrieval-Augmented Time Series Forecasting (SARAF), a framework that adaptively balances relevance and diversity in retrieval. SARAF first forms a candidate pool via temporal similarity with time-aligned enhancement, then applies a diversity-aware selection strategy to cover heterogeneous historical regimes, with the diversification strength automatically modulated by dataset-level stationarity. Moreover, SARAF uses stationarity-aware aggregation to fuse the retrieved futures. Extensive experiments on eight real-world datasets show that SARAF achieves competitive forecasting performance and improves average accuracy and robustness over strong baselines, with particularly clear benefits under challenging non-stationary settings. Code: https://github.com/ShiqiaoZhou/SARAF.

Huanbo Lyu, Miqing Li, Shiqiao Zhou et al.

In offline data-driven multi-objective optimization (MOO), optimization is performed using surrogate models trained only on an offline dataset. These surrogate models contain inherent errors and uncertainty. This epistemic uncertainty can lead to incorrect dominance judgments, thereby misleading the search process. Existing methods mitigate this issue by incorporating uncertainty estimates from Gaussian Process Regression (GPR) to correct dominance judgments; however, they are restricted to GPR, and their optimization strategies cannot be scaled to other uncertainty quantification methods. In addition, GPR-based surrogates suffer from high computational cost. We propose a simple yet effective dual-ranking strategy that flexibly leverages both predictive results and uncertainty estimates from different surrogate models. By performing non-dominated sorting on candidate solutions using both surrogate-based fitness values and uncertainty-aware fitness values, the proposed method prioritizes candidate solutions that are simultaneously high-quality and reliable. Through extensive experimental evaluations, including ablation, sensitivity, and comparative experiments, we demonstrate the effectiveness and robustness of the proposed dual-ranking strategy working with different surrogates. Our dual-ranking framework offers more robust solutions for data-limited, real-world applications.

Shiqiao Zhou, Holger Schöner, Huanbo Lyu et al.

Time series forecasting is a long-standing and highly challenging research topic. Recently, driven by the rise of large language models (LLMs), research has increasingly shifted from purely time series methods toward harnessing textual modalities to enhance forecasting performance. However, the vast discrepancy between text and temporal data often leads current multimodal architectures to over-emphasise one modality while neglecting the other, resulting in information loss that harms forecasting performance. To address this modality imbalance, we introduce BALM-TSF (Balanced Multimodal Alignment for LLM-Based Time Series Forecasting), a lightweight time series forecasting framework that maintains balance between the two modalities. Specifically, raw time series are processed by the time series encoder, while descriptive statistics of raw time series are fed to an LLM with learnable prompt, producing compact textual embeddings. To ensure balanced cross-modal context alignment of time series and textual embeddings, a simple yet effective scaling strategy combined with a contrastive objective then maps these textual embeddings into the latent space of the time series embeddings. Finally, the aligned textual semantic embeddings and time series embeddings are together integrated for forecasting. Extensive experiments on standard benchmarks show that, with minimal trainable parameters, BALM-TSF achieves state-of-the-art performance in both long-term and few-shot forecasting, confirming its ability to harness complementary information from text and time series. Code is available at https://github.com/ShiqiaoZhou/BALM-TSF.