Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression
This addresses domain adaptation for regression tasks, which is important for applications like battery prediction, but it is incremental as it builds on existing alignment methods by adding uncertainty guidance.
The paper tackles the problem of unsupervised domain adaptation for regression by proposing Uncertainty-Guided Alignment, which integrates predictive uncertainty into feature alignment to mitigate issues like feature collapse. The method outperforms state-of-the-art methods across 52 transfer tasks on benchmarks including computer vision and battery state-of-charge prediction.
Unsupervised Domain Adaptation for Regression (UDAR) aims to adapt models from a labeled source domain to an unlabeled target domain for regression tasks. Traditional feature alignment methods, successful in classification, often prove ineffective for regression due to the correlated nature of regression features. To address this challenge, we propose Uncertainty-Guided Alignment (UGA), a novel method that integrates predictive uncertainty into the feature alignment process. UGA employs Evidential Deep Learning to predict both target values and their associated uncertainties. This uncertainty information guides the alignment process and fuses information within the embedding space, effectively mitigating issues such as feature collapse in out-of-distribution scenarios. We evaluate UGA on two computer vision benchmarks and a real-world battery state-of-charge prediction across different manufacturers and operating temperatures. Across 52 transfer tasks, UGA on average outperforms existing state-of-the-art methods. Our approach not only improves adaptation performance but also provides well-calibrated uncertainty estimates.