ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems
This addresses the issue of tedious model updating and deployment in MLOps for ML teams, but it is incremental as it builds on existing continual learning and deployment techniques.
The paper tackles the problem of dynamic environments in ML serving systems where online data diverges from offline training data, by implementing ModelCI-e, a lightweight MLOps plugin that enables continual learning for model updating and validation without customizing serving engines, with preliminary results showing improved usability and highlighting the importance of separating updating and inference workloads for efficiency.
MLOps is about taking experimental ML models to production, i.e., serving the models to actual users. Unfortunately, existing ML serving systems do not adequately handle the dynamic environments in which online data diverges from offline training data, resulting in tedious model updating and deployment works. This paper implements a lightweight MLOps plugin, termed ModelCI-e (continuous integration and evolution), to address the issue. Specifically, it embraces continual learning (CL) and ML deployment techniques, providing end-to-end supports for model updating and validation without serving engine customization. ModelCI-e includes 1) a model factory that allows CL researchers to prototype and benchmark CL models with ease, 2) a CL backend to automate and orchestrate the model updating efficiently, and 3) a web interface for an ML team to manage CL service collaboratively. Our preliminary results demonstrate the usability of ModelCI-e, and indicate that eliminating the interference between model updating and inference workloads is crucial for higher system efficiency.