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

MLOps is about taking experimental ML models to production, i.e., serving themodels to actual users. Unfortunately, existing ML serving systems do notadequately handle the dynamic environments in which online data diverges fromoffline training data, resulting in tedious model updating and deploymentworks. This paper implements a lightweight MLOps plugin, termed ModelCI-e(continuous integration and evolution), to address the issue. Specifically, itembraces continual learning (CL) and ML deployment techniques, providingend-to-end supports for model updating and validation without serving enginecustomization. ModelCI-e includes 1) a model factory that allows CL researchersto prototype and benchmark CL models with ease, 2) a CL backend to automate andorchestrate the model updating efficiently, and 3) a web interface for an MLteam to manage CL service collaboratively. Our preliminary results demonstratethe usability of ModelCI-e, and indicate that eliminating the interferencebetween model updating and inference workloads is crucial for higher systemefficiency.

ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems