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

Classical federated learning approaches yield significant performancedegradation in the presence of Non-IID data distributions of participants. Whenthe distribution of each local dataset is highly different from the global one,the local objective of each client will be inconsistent with the global optimawhich incur a drift in the local updates. This phenomenon highly impacts theperformance of clients. This is while the primary incentive for clients toparticipate in federated learning is to obtain better personalized models. Toaddress the above-mentioned issue, we present a new algorithm, FLIS, whichgroups the clients population in clusters with jointly trainable datadistributions by leveraging the inference similarity of clients' models. Thisframework captures settings where different groups of users have their ownobjectives (learning tasks) but by aggregating their data with others in thesame cluster (same learning task) to perform more efficient and personalizedfederated learning. We present experimental results to demonstrate the benefitsof FLIS over the state-of-the-art benchmarks on CIFAR-100/10, SVHN, and FMNISTdatasets. Our code is available at https://github.com/MMorafah/FLIS.

FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution