{"ID":2869163,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14642","arxiv_id":"2509.14642","title":"DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training","abstract":"Modeling dynamic temporal dependencies is a critical challenge in time series pre-training, which evolve due to distribution shifts and multi-scale patterns. This temporal variability severely impairs the generalization of pre-trained models to downstream tasks. Existing frameworks fail to capture the complex interactions of short- and long-term dependencies, making them susceptible to spurious correlations that degrade generalization. To address these limitations, we propose DeCoP, a Dependency Controlled Pre-training framework that explicitly models dynamic, multi-scale dependencies by simulating evolving inter-patch dependencies. At the input level, DeCoP introduces Instance-wise Patch Normalization (IPN) to mitigate distributional shifts while preserving the unique characteristics of each patch, creating a robust foundation for representation learning. At the latent level, a hierarchical Dependency Controlled Learning (DCL) strategy explicitly models inter-patch dependencies across multiple temporal scales, with an Instance-level Contrastive Module (ICM) enhances global generalization by learning instance-discriminative representations from time-invariant positive pairs. DeCoP achieves state-of-the-art results on ten datasets with lower computing resources, improving MSE by 3% on ETTh1 over PatchTST using only 37% of the FLOPs.","short_abstract":"Modeling dynamic temporal dependencies is a critical challenge in time series pre-training, which evolve due to distribution shifts and multi-scale patterns. This temporal variability severely impairs the generalization of pre-trained models to downstream tasks. Existing frameworks fail to capture the complex interacti...","url_abs":"https://arxiv.org/abs/2509.14642","url_pdf":"https://arxiv.org/pdf/2509.14642v1","authors":"[\"Yuemin Wu\",\"Zhongze Wu\",\"Xiu Su\",\"Feng Yang\",\"Hongyan Xu\",\"Xi Lin\",\"Wenti Huang\",\"Shan You\",\"Chang Xu\"]","published":"2025-09-18T05:44:06Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}