paper-with-me

홈 › Papers

Active Online Domain Adaptation

2020-06-12 · ICML Workshop LifelongML 2020 7 · Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang

Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in settings where the data streams are from a mixture of hidden domains. For online linear regression with oblivious adversaries, we provide a tight tradeoff that depends on the durations and dimensionalities of the hidden domains. Our algorithm can adaptively deal with interleaving spans of inputs from different domains. We also generalize our results to non-linear regression for hypothesis classes with bounded eluder dimension and adaptive adversaries. Experiments on synthetic and realistic datasets demonstrate that our algorithm achieves lower regret than uniform queries and greedy queries with equal labeling budget.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationOnline Domain Adaptationregression

Similar Papers 제목 키워드 기반

ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentation

2023-12-08 · Md Shazid Islam, Sayak Nag, Arindam Dutta, Miraj Ahmed 외

Unsupervised domain adaptive segmentation typically relies on self-training using pseudo labels predicted by a pre-trained network on an unlabeled target dataset. However, the noisy nature of such pseudo-labels presents …

Active LearningDomain AdaptationFederated LearningImage Segmentation+4

Online Active Learning for Cost Sensitive Domain Adaptation

2013-08-01 · WS 2013 8 · Min Xiao, Yuhong Guo
Active LearningDomain AdaptationSentiment Analysis

A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits

2017-12-13 · Sariya Karimova, Patrick Simianer, Stefan Riezler

The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive …

Machine TranslationNMTTranslation

Online Continual Adaptation with Active Self-Training

2021-06-11 · Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang 외

Models trained with offline data often suffer from continual distribution shifts and expensive labeling in changing environments. This calls for a new online learning paradigm where the learner can continually adapt to c…

Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning

2021-10-01 · Dongseong Hwang, Ananya Misra, Zhouyuan Huo, Nikhil Siddhartha 외

Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on in-domain performance for public datasets…

Domain Adaptation