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 (FL) aims to collaboratively train a global model whileensuring client data privacy. However, FL faces challenges from the non-IIDdata distribution among clients. Clustered FL (CFL) has emerged as a promisingsolution, but most existing CFL frameworks adopt synchronous frameworks lackingasynchrony. An asynchronous CFL framework called SDAGFL based on directedacyclic graph distributed ledger techniques (DAG-DLT) was proposed, but itscomplete decentralization leads to high communication and storage costs. Wepropose DAG-ACFL, an asynchronous clustered FL framework based on directedacyclic graph distributed ledger techniques (DAG-DLT). We first detail thecomponents of DAG-ACFL. A tip selection algorithm based on the cosinesimilarity of model parameters is then designed to aggregate models fromclients with similar distributions. An adaptive tip selection algorithmleveraging change-point detection dynamically determines the number of selectedtips. We evaluate the clustering and training performance of DAG-ACFL onmultiple datasets and analyze its communication and storage costs. Experimentsshow the superiority of DAG-ACFL in asynchronous clustered FL. By combiningDAG-DLT with clustered FL, DAG-ACFL realizes robust, decentralized and privatemodel training with efficient performance.

DAG-ACFL: Asynchronous Clustered Federated Learning based on DAG-DLT