paper-with-me

Papers

Evolving Domain Generalization

2022-05-31 · William Wei Wang, Gezheng Xu, Ruizhi Pu, Jiaqi Li, Fan Zhou, Changjian Shui, Charles Ling, Christian Gagné, Boyu Wang

Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data. Existing domain generalization methods ignore the relationship between tasks, implicitly assuming that all the tasks are sampled from a stationary environment. Therefore, they can fail when deployed in an evolving environment. To this end, we formulate and study the \emph{evolving domain generalization} (EDG) scenario, which exploits not only the source data but also their evolving pattern to generate a model for the unseen task. Our theoretical result reveals the benefits of modeling the relation between two consecutive tasks by learning a globally consistent directional mapping function. In practice, our analysis also suggests solving the DDG problem in a meta-learning manner, which leads to \emph{directional prototypical network}, the first method for the DDG problem. Empirical evaluation of both synthetic and real-world data sets validates the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2206.00047

Code (0)

등록된 구현이 없습니다.

Tasks

Domain GeneralizationEvolving Domain GeneralizationMeta-Learning

Similar Papers 제목 키워드 기반

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

2024-01-16 · Binghui Xie, Yongqiang Chen, Jiaqi Wang, Kaiwen Zhou 외

Domain generalization is a critical challenge for machine learning systems. Prior domain generalization methods focus on extracting domain-invariant features across several stationary domains to enable generalization to …

Domain GeneralizationEvolving Domain Generalization

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

2022-05-16 · Tiexin Qin, Shiqi Wang, Haoliang Li

Domain generalization aims to improve the generalization capability of machine learning systems to out-of-distribution (OOD) data. Existing domain generalization techniques embark upon stationary and discrete environment…

Domain GeneralizationEvolving Domain Generalization

Generalizing across Temporal Domains with Koopman Operators

2024-02-12 · Qiuhao Zeng, Wei Wang, Fan Zhou, Gezheng Xu 외

In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes further complicated wh…

Domain GeneralizationGeneralization Bounds

Evolving Standardization for Continual Domain Generalization over Temporal Drift

2023-09-21 · NeurIPS 2023 11

The capability of generalizing to out-of-distribution data is crucial for the deployment of machine learning models in the real world. Existing domain generalization (DG) mainly embarks on offline and discrete scenarios,…

Directional Domain Generalization

2021-09-29 · Wei Wang, Jiaqi Li, Ruizhi Pu, Gezheng Xu 외

Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data. Existing domain generalizat…

Domain GeneralizationMeta-LearningRelation