Imputing missing values in multivariate time series remains challenging, especially under diverse missing patterns and heavy missingness. Existing methods suffer from suboptimal performance as corrupted temporal features hinder effective cross-variable information transfer, amplifying reconstruction errors. Robust imputation requires both extracting temporal patterns from sparse observations within each variable and selectively transferring information across variables--yet current approaches excel at one while compromising the other. We introduce T1 (Time series imputation with 1-to-1 channel-head binding), a CNN-Transformer hybrid architecture that achieves robust imputation through Channel-Head Binding--a mechanism creating one-to-one correspondence between CNN channels and attention heads. This design enables selective information transfer: when missingness corrupts certain temporal patterns, their corresponding attention pathways adaptively down-weight based on remaining observable patterns while preserving reliable cross-variable connections through unaffected channels. Experiments on 11 benchmark datasets demonstrate that T1 achieves state-of-the-art performance, reducing MSE by 46% on average compared to the second-best baseline, with particularly strong gains under extreme sparsity (70% missing ratio). The model generalizes to unseen missing patterns without retraining and uses a consistent hyperparameter configuration across all datasets. The code is available at https://github.com/Oppenheimerdinger/T1.

翻译：多元时间序列中的缺失值插补仍然具有挑战性，尤其是在多样的缺失模式和严重缺失情况下。现有方法性能欠佳，因为受损的时间特征阻碍了有效的跨变量信息传递，从而放大了重建误差。稳健的插补既需要从每个变量内的稀疏观测中提取时间模式，又需要跨变量选择性地传递信息——然而当前方法往往擅长一方面而牺牲另一方面。我们提出了T1（采用一对一通道-头绑定的时间序列插补方法），这是一种CNN-Transformer混合架构，通过通道-头绑定机制实现稳健插补——该机制在CNN通道和注意力头之间建立了一一对应关系。这种设计实现了选择性信息传递：当缺失破坏了某些时间模式时，其对应的注意力通路会根据剩余可观测模式自适应地降低权重，同时通过未受影响的通道保持可靠的跨变量连接。在11个基准数据集上的实验表明，T1实现了最先进的性能，与次优基线相比平均降低了46%的均方误差，在极端稀疏性（70%缺失率）下提升尤为显著。该模型无需重新训练即可泛化到未见过的缺失模式，并在所有数据集上使用一致的超参数配置。代码可在 https://github.com/Oppenheimerdinger/T1 获取。