Label Shift Meets Online Learning: Ensuring Consistent Adaptation with Universal Dynamic Regret
Label shift, which investigates the adaptation of label distributions between the fixed source and target domains, has attracted significant research interests and broad applications in offline settings. In real-world scenarios, however, data often arrives as a continuous stream. Addressing label shift in online learning settings is paramount. Existing strategies, which tailor traditional offline label shift techniques to online settings, have degraded performance due to the inconsistent estimation of label distributions and violation of convex assumption for theoretical guarantee. In this paper, we propose a novel method to ensure consistent adaptation to online label shift. We construct a new convex risk estimator that is pivotal for both online optimization and theoretical analysis. Furthermore, we enhance an optimistic online algorithm as the base learner and refine the classifier using an ensemble method. Theoretically, we derive a universal dynamic regret which achieves minimax optimal. Extensive experiments on both real-world datasets and human motion task demonstrate the superiority of our method comparing existing methods.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
This paper focuses on supervised and unsupervised online label shift, where the class marginals $Q(y)$ varies but the class-conditionals $Q(x|y)$ remain invariant. In the unsupervised setting, our goal is to adapt a lear…
Overcoming label shift in targeted federated learning
Federated learning enables multiple actors to collaboratively train models without sharing private data. This unlocks the potential for scaling machine learning to diverse applications. Existing algorithms for this task …
Federated Learningimage-classificationImage ClassificationEstimating calibration error under label shift without labels
In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems. Calibration error (CE) is an indicator of the alignment between the predicted probabilities an…
ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate
In real-world applications, machine learning models face online label shift, where label distributions change over time. Effective adaptation requires careful learning rate selection: too low slows adaptation and too hig…
Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)
Vision-language models like Contrastive Language-Image Pre-Training (CLIP) have been extensively studied in data-scarce scenarios. A particularly challenging and realistic task in this area is online zero-shot learning w…
Zero-Shot LearningDomain Adaptation