具有时间插补的证据校准无源时间序列域适应
Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation
AI总结：
针对时间序列 SFDA 中时间动态建模不足与 softmax 过度自信问题，提出 MAPU 时间插补框架及引入证据不确定性校准的 E-MAPU，并在五个真实数据集上验证显著优于现有方法。
摘要：
无源域适应（SFDA）旨在在无法访问源数据的情况下，将在带标签源域上预训练的模型适应到无标签目标域，从而保护源域隐私。尽管 SFDA 在计算机视觉中十分普遍，但它在时间序列分析中仍基本未被探索。现有为视觉数据设计的 SFDA 方法难以捕捉时间序列固有的时间动态，从而阻碍了适应性能。本文提出 MAsk And imPUte（MAPU），这是一种新颖且有效的时间序列 SFDA 方法。MAPU 通过引入一种新的时间插补任务来应对时间一致性这一关键挑战。该任务包括随机遮蔽时间序列信号，并利用专用的时间插补器在学习到的嵌入空间内恢复原始信号，从而避开含噪原始数据的复杂性。值得注意的是，MAPU 是首个在时间序列 SFDA 背景下显式处理时间一致性的方法。此外，它能够与现有 SFDA 方法无缝集成，提供更高的灵活性。我们进一步提出 E-MAPU，该方法结合证据不确定性估计，以解决 softmax 预测中固有的过度自信问题。为实现这一点，我们利用证据深度学习获得校准更好的预训练模型，并调整目标编码器，将处于支持集之外的目标样本映射到更接近源域支持集的新特征表示。这促进了更好的对齐，最终提升适应性能。在五个真实世界时间序列数据集上的大量实验表明，与现有方法相比，MAPU 和 E-MAPU 均取得显著性能提升。这些结果凸显了我们所提方法在解决各类时间序列域适应问题方面的有效性。
英文摘要：
Source-free domain adaptation (SFDA) aims to adapt a model pre-trained on a labeled source domain to an unlabeled target domain without access to source data, preserving the source domain's privacy. While SFDA is prevalent in computer vision, it remains largely unexplored in time series analysis. Existing SFDA methods, designed for visual data, struggle to capture the inherent temporal dynamics of time series, hindering adaptation performance. This paper proposes MAsk And imPUte (MAPU), a novel and effective approach for time series SFDA. MAPU addresses the critical challenge of temporal consistency by introducing a novel temporal imputation task. This task involves randomly masking time series signals and leveraging a dedicated temporal imputer to recover the original signal within the learned embedding space, bypassing the complexities of noisy raw data. Notably, MAPU is the first method to explicitly address temporal consistency in the context of time series SFDA. Additionally, it offers seamless integration with existing SFDA methods, providing greater flexibility. We further introduce E-MAPU, which incorporates evidential uncertainty estimation to address the overconfidence issue inherent in softmax predictions. To achieve that, we leverage evidential deep learning to obtain a better-calibrated pre-trained model and adapt the target encoder to map out-of-support target samples to a new feature representation closer to the source domain's support. This fosters better alignment, ultimately enhancing adaptation performance. Extensive experiments on five real-world time series datasets demonstrate that both MAPU and E-MAPU achieve significant performance gains compared to existing methods. These results highlight the effectiveness of our proposed approaches for tackling various time series domain adaptation problems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
