English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Domain generalization aims to improve the generalization capability ofmachine learning systems to out-of-distribution (OOD) data. Existing domaingeneralization techniques embark upon stationary and discrete environments totackle the generalization issue caused by OOD data. However, many real-worldtasks in non-stationary environments (e.g. self-driven car system, sensormeasures) involve more complex and continuously evolving domain drift, whichraises new challenges for the problem of domain generalization. In this paper,we formulate the aforementioned setting as the problem of evolving domaingeneralization. Specifically, we propose to introduce a probabilistic frameworkcalled Latent Structure-aware Sequential Autoencoder (LSSAE) to tackle theproblem of evolving domain generalization via exploring the underlyingcontinuous structure in the latent space of deep neural networks, where we aimto identify two major factors namely covariate shift and concept shiftaccounting for distribution shift in non-stationary environments. Experimentalresults on both synthetic and real-world datasets show that LSSAE can lead tosuperior performances based on the evolving domain generalization setting.

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder