用可学习的特征身份提升时间序列填补效果
HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
- 为每个特征分配持久的可学习身份嵌入，保持语义一致性
- 在5个数据集21组实验中超越16个基线方法
- 适合处理混合空间位置与语义变量的数据
时间序列填补依赖于跨特征相关性，但现有基于注意力的方法在每层重新发现特征关系，缺乏持续的锚点以维持一致表示。为此，我们提出HELIX，为每个特征分配可学习的特征身份，即在整个网络中捕捉内在语义属性的持久嵌入。不同于依赖预设拓扑、假设同质空间关系的图方法，HELIX从时间共变性端到端学习任意特征依赖，自然处理特征混合空间位置与语义变量的数据集。结合混合时序-特征注意力，HELIX在5个公开数据集、21种实验设置中超越全部16个基线。机制分析表明，HELIX随层加深逐步对齐学习到的特征身份与依赖关系与潜在物理和语义结构，证明其更有效将跨特征结构转化为填补精度。
原文摘要 · Abstract (English)
Time series imputation benefits from leveraging cross-feature correlations, yet existing attention-based methods re-discover feature relationships at each layer, lacking persistent anchors to maintain consistent representations. To address this, we propose HELIX, which assigns each feature a learnable feature identity, a persistent embedding that captures intrinsic semantic properties throughout the network. Unlike graph-based methods that rely on predefined topology and assume homogeneous spatial relationships, HELIX learns arbitrary feature dependencies end-to-end from temporal co-variation, naturally handling datasets where features mix spatial locations with semantic variables. Integrated with hybrid temporal-feature attention, HELIX achieves the state-of-the-art performance, surpassing all 16 baselines on 5 public datasets across 21 experimental settings in our evaluation. Furthermore, our mechanistic analysis reveals that HELIX aligns learned feature identities and dependencies with latent physical and semantic structure progressively across layers, demonstrating that it more effectively translates cross-feature structure into imputation accuracy.
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。