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

Out-of-distribution (OOD) generalization is indispensable for learning modelsin the wild, where testing distribution typically unknown and different fromthe training. Recent methods derived from causality have shown great potentialin achieving OOD generalization. However, existing methods mainly focus on theinvariance property of causes, while largely overlooking the property of\textit{sufficiency} and \textit{necessity} conditions. Namely, a necessary butinsufficient cause (feature) is invariant to distribution shift, yet it may nothave required accuracy. By contrast, a sufficient yet unnecessary cause(feature) tends to fit specific data well but may have a risk of adapting to anew domain. To capture the information of sufficient and necessary causes, weemploy a classical concept, the probability of sufficiency and necessary causes(PNS), which indicates the probability of whether one is the necessary andsufficient cause. To associate PNS with OOD generalization, we propose PNS riskand formulate an algorithm to learn representation with a high PNS value. Wetheoretically analyze and prove the generalizability of the PNS risk.Experiments on both synthetic and real-world benchmarks demonstrate theeffectiveness of the proposed method. The details of the implementation can befound at the GitHub repository: https://github.com/ymy4323460/CaSN.

Invariant Learning via Probability of Sufficient and Necessary Causes