Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these algorithms ineffective. Prior solutions to the OOD challenge seek to identify invariant features across different training domains. The underlying assumption is that these invariant features should also work reasonably well in the unlabeled target domain. By contrast, this work is interested in the domain-specific features that include both invariant features and features unique to the target domain. We propose a simple yet effective approach that relies on correlations in general regardless of whether the features are invariant or not. Our approach uses the most confidently predicted samples identified by an OOD base model (teacher model) to train a new model (student model) that effectively adapts to the target domain. Empirical evaluations on benchmark datasets show that the performance is improved over the SOTA by ∼10-20%.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 IEEE International Conference on Big Data, Big Data 2022
EditorsShusaku Tsumoto, Yukio Ohsawa, Lei Chen, Dirk Van den Poel, Xiaohua Hu, Yoichi Motomura, Takuya Takagi, Lingfei Wu, Ying Xie, Akihiro Abe, Vijay Raghavan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Electronic)9781665480451
StatePublished - 2022
Event2022 IEEE International Conference on Big Data, Big Data 2022 - Osaka, Japan
Duration: Dec 17 2022Dec 20 2022

Publication series

NameProceedings - 2022 IEEE International Conference on Big Data, Big Data 2022


Conference2022 IEEE International Conference on Big Data, Big Data 2022

ASJC Scopus subject areas

  • Modeling and Simulation
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Control and Optimization


Dive into the research topics of 'Distributional Shift Adaptation using Domain-Specific Features'. Together they form a unique fingerprint.

Cite this