面向视频与时间序列的因果最优传输不确定性感知无监督域自适应
Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transport
将因果图正则化嵌入最优传输对齐过程，为视频域自适应提供了一种同时对齐特征分布与因果结构的可复用框架，其基于熵与结构一致性的伪标签筛选策略可直接用于提升自训练稳定性。
原文依据 we propose a novel UDA framework, named Causally-Regularized Optimal Transport (in short Causal-OT), that preserves domain-invariant causal mechanisms by embedding causal graph regularization into robust OT alignment process.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频和1D时间序列的无监督域自适应（UDA）面临时序动态与特征分布两方面域偏移带来的显著挑战。现有面向时间序列的UDA方法通常将时序对齐与不确定性缓解作为独立目标处理，导致训练不稳定、伪标签噪声大以及特征迁移不完整。这种割裂处理无法捕捉通道间的因果依赖，也忽略了预测不确定性对自适应质量的影响，从而限制了所学表示的可迁移性并导致次优的自适应效果。为解决上述局限，我们提出了一种新的UDA框架，名为因果正则化最优传输（简称Causal-OT），通过将因果图正则化嵌入鲁棒最优传输对齐过程来保持域不变的因果机制。首先，我们在源域和目标域中估计通道间因果图，并学习一个传输方案，该方案不仅对齐特征分布，还提升可解释性并最小化格兰杰图因果结构之间的差异。然而，伪标签仍可能容易发生错误传播，在自训练过程中允许错误的目标预测，降低模型稳定性与跨域迁移质量。为缓解这一问题，我们进一步引入一种因果感知的伪标签策略，基于熵和与源域因果图的结构一致性来选择高置信度的目标样本。这增强了对伪标签噪声的鲁棒性。在六个时间序列基准上的大量实验取得了4.5%的准确率提升和3.8%的F1分数提升。我们在四个基准视频数据集上进行实验，取得了2.5%的准确率提升。
英文原文摘要 1854 字符
Unsupervised domain adaptation (UDA) for videos and 1D time-series data faces significant challenges due to domain shifts in terms of both temporal dynamics and feature distributions. Existing UDA approaches for time-series data often address temporal alignment and uncertainty mitigation as separate objectives, leading to unstable training, noisy pseudo-labels, and incomplete feature transfer. This disjoint treatment fails to capture inter-channel causal dependencies and also overlooks the impact of prediction uncertainty on adaptation quality. This limits the transferability of learned representations and results in suboptimal adaptation. To address the aforementioned limitations, we propose a novel UDA framework, named Causally-Regularized Optimal Transport (in short Causal-OT), that preserves domain-invariant causal mechanisms by embedding causal graph regularization into robust OT alignment process. First we estimate inter-channel causal graphs in both source and target domains and learn a transport plan that not only aligns feature distributions but also improves interpretability and minimizes the discrepancy between causal structures of the Granger graphs. However, pseudo-labeling may still prone to error propagation allowing incorrect target predictions during self-training, degrading the model stability and transfer quality across domains. To mitigate this, we further introduce a causality-aware pseudo-labeling strategy that selects high-confidence target samples based on both entropy and structural consistency with the causal graph of the source domain. This enhances robustness against pseudo-label noise.Extensive experiments on six time-series benchmarks achieving 4.5% gain in accuracy and a 3.8% improvement in F1-score. We conduct experiments on four benchmark video datasets that achieve a 2.5% gain in accuracy.