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

While providing machine learning model as a service to process users'inference requests, online applications can periodically upgrade the modelutilizing newly collected data. Federated learning (FL) is beneficial forenabling the training of models across distributed clients while keeping thedata locally. However, existing work has overlooked the coexistence of modeltraining and inference under clients' limited resources. This paper focuses onthe joint optimization of model training and inference to maximize inferenceperformance at clients. Such an optimization faces several challenges. Thefirst challenge is to characterize the clients' inference performance whenclients may partially participate in FL. To resolve this challenge, weintroduce a new notion of age of model (AoM) to quantify client-side modelfreshness, based on which we use FL's global model convergence error as anapproximate measure of inference performance. The second challenge is the tightcoupling among clients' decisions, including participation probability in FL,model download probability, and service rates. Toward the challenges, wepropose an online problem approximation to reduce the problem complexity andoptimize the resources to balance the needs of model training and inference.Experimental results demonstrate that the proposed algorithm improves theaverage inference accuracy by up to 12%.

Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization