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

In federated learning (FL), it is commonly assumed that all data are placedat clients in the beginning of machine learning (ML) optimization (i.e.,offline learning). However, in many real-world applications, it is expected toproceed in an online fashion. To this end, online FL (OFL) has been introduced,which aims at learning a sequence of global models from decentralized streamingdata such that the so-called cumulative regret is minimized. Combining onlinegradient descent and model averaging, in this framework, FedOGD is constructedas the counterpart of FedSGD in FL. While it can enjoy an optimal sublinearregret, FedOGD suffers from heavy communication costs. In this paper, wepresent a communication-efficient method (named OFedIQ) by means ofintermittent transmission (enabled by client subsampling and periodictransmission) and quantization. For the first time, we derive the regret boundthat captures the impact of data-heterogeneity and the communication-efficienttechniques. Through this, we efficiently optimize the parameters of OFedIQ suchas sampling rate, transmission period, and quantization levels. Also, it isproved that the optimized OFedIQ can asymptotically achieve the performance ofFedOGD while reducing the communication costs by 99%. Via experiments with realdatasets, we demonstrate the effectiveness of the optimized OFedIQ.

Tighter Regret Analysis and Optimization of Online Federated Learning