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 collaborative learning paradigm fordecentralized private data from mobile terminals (MTs). However, it suffersfrom issues in terms of communication, resource of MTs, and privacy. Existingprivacy-preserving FL methods usually adopt the instance-level differentialprivacy (DP), which provides a rigorous privacy guarantee but with severalbottlenecks: severe performance degradation, transmission overhead, andresource constraints of edge devices such as MTs. To overcome these drawbacks,we propose Fed-LTP, an efficient and privacy-enhanced FL framework with\underline{\textbf{L}}ottery \underline{\textbf{T}}icket\underline{\textbf{H}}ypothesis (LTH) and zero-concentratedD\underline{\textbf{P}} (zCDP). It generates a pruned global model on theserver side and conducts sparse-to-sparse training from scratch with zCDP onthe client side. On the server side, two pruning schemes are proposed: (i) theweight-based pruning (LTH) determines the pruned global model structure; (ii)the iterative pruning further shrinks the size of the pruned model'sparameters. Meanwhile, the performance of Fed-LTP is also boosted via modelvalidation based on the Laplace mechanism. On the client side, we usesparse-to-sparse training to solve the resource-constraints issue and providetighter privacy analysis to reduce the privacy budget. We evaluate theeffectiveness of Fed-LTP on several real-world datasets in both independent andidentically distributed (IID) and non-IID settings. The results clearly confirmthe superiority of Fed-LTP over state-of-the-art (SOTA) methods incommunication, computation, and memory efficiencies while realizing a betterutility-privacy trade-off.

Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing