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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Federated learning (FL) is a distributed framework for collaborativelytraining with privacy guarantees. In real-world scenarios, clients may haveNon-IID data (local class imbalance) with poor annotation quality (labelnoise). The co-existence of label noise and class imbalance in FL's small localdatasets renders conventional FL methods and noisy-label learning methods bothineffective. To address the challenges, we propose FedCNI without using anadditional clean proxy dataset. It includes a noise-resilient local solver anda robust global aggregator. For the local solver, we design a more robustprototypical noise detector to distinguish noisy samples. Further to reduce thenegative impact brought by the noisy samples, we devise a curriculum pseudolabeling method and a denoise Mixup training strategy. For the globalaggregator, we propose a switching re-weighted aggregation method tailored todifferent learning periods. Extensive experiments demonstrate our method cansubstantially outperform state-of-the-art solutions in mix-heterogeneous FLenvironments.

Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients