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

Pre-trained models are widely used in fine-tuning downstream tasks withlinear classifiers optimized by the cross-entropy loss, which might facerobustness and stability problems. These problems can be improved by learningrepresentations that focus on similarities in the same class and contradictionsin different classes when making predictions. In this paper, we utilize theK-Nearest Neighbors Classifier in pre-trained model fine-tuning. For this KNNclassifier, we introduce a supervised momentum contrastive learning frameworkto learn the clustered representations of the supervised downstream tasks.Extensive experiments on text classification tasks and robustness tests showthat by incorporating KNNs with the traditional fine-tuning process, we canobtain significant improvements on the clean accuracy in both rich-source andfew-shot settings and can improve the robustness against adversarial attacks.\footnote{all codes is available at https://github.com/LinyangLee/KNN-BERT}

KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier