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

Federated learning allows multiple clients to collaborate to trainhigh-performance deep learning models while keeping the training data locally.However, when the local data of all clients are not independent and identicallydistributed (i.e., non-IID), it is challenging to implement this form ofefficient collaborative learning. Although significant efforts have beendedicated to addressing this challenge, the effect on the image classificationtask is still not satisfactory. In this paper, we propose FedProc: prototypicalcontrastive federated learning, which is a simple and effective federatedlearning framework. The key idea is to utilize the prototypes as globalknowledge to correct the local training of each client. We design a localnetwork architecture and a global prototypical contrastive loss to regulate thetraining of local models, which makes local objectives consistent with theglobal optima. Eventually, the converged global model obtains a goodperformance on non-IID data. Experimental results show that, compared tostate-of-the-art federated learning methods, FedProc improves the accuracy by$1.6\%\sim7.9\%$ with acceptable computation cost.

FedProc: Prototypical Contrastive Federated Learning on Non-IID data