动态分块压缩时间序列，提升预测效率与精度
TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting
- 根据信号复杂度自适应调整分块大小，关键区域细分、平滑区粗分
- 预训练阶段实现20倍加速、8倍数据效率提升，长程预测更优
- 适合大规模时序建模，尤其在长序列高维场景下表现突出
基于Transformer的时间序列基础模型在分词策略上面临根本权衡：逐点嵌入保留时间保真度但随序列长度增长而效率低下；固定长度分块虽提升效率，却可能破坏自然过渡并模糊局部有效动态。为此，我们提出动态分块机制TimeSqueeze，依据每条序列的局部信号复杂度自适应选择分块边界。首先通过轻量级状态空间编码器提取全分辨率逐点特征，再基于内容感知进行分割：信息密集区域分配短分块，平滑或冗余段落使用长分块。这种变分辨率压缩在保留关键时间结构的同时显著减少输入Transformer主干的标记序列长度。在大规模预训练中，TimeSqueeze相比等效逐点基线实现最高20倍更快收敛和8倍更高的数据效率。在多组长程预测基准测试中，其性能持续优于采用逐点分词或固定尺寸分块的同类架构。
原文摘要 · Abstract (English)
Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with sequence length, whereas fixed-length patching improves efficiency by imposing uniform boundaries that may disrupt natural transitions and blur informative local dynamics. In order to address these limitations, we introduce TimeSqueeze, a dynamic patching mechanism that adaptively selects patch boundaries within each sequence based on local signal complexity. TimeSqueeze first applies a lightweight state-space encoder to extract full-resolution point-wise features, then performs content-aware segmentation by allocating short patches to information-dense regions and long patches to smooth or redundant segments. This variable-resolution compression preserves critical temporal structure while substantially reducing the token sequence presented to the Transformer backbone. Specifically for large-scale pretraining, TimeSqueeze attains up to 20x faster convergence and 8x higher data efficiency compared to equivalent point-token baselines. Experiments across long-horizon forecasting benchmarks show that TimeSqueeze consistently outperforms comparable architectures that use either point-wise tokenization or fixed-size patching.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。