Differential Replication in Machine Learning
This addresses the challenge of model adaptability for real-world applications, but it appears incremental as it builds on existing ideas of knowledge reuse.
The paper tackles the problem of machine learning models needing to adapt to changing data and requirements in deployment by proposing differential replication, which reuses knowledge from deployed models to train future generations.
When deployed in the wild, machine learning models are usually confronted with data and requirements that constantly vary, either because of changes in the generating distribution or because external constraints change the environment where the model operates. To survive in such an ecosystem, machine learning models need to adapt to new conditions by evolving over time. The idea of model adaptability has been studied from different perspectives. In this paper, we propose a solution based on reusing the knowledge acquired by the already deployed machine learning models and leveraging it to train future generations. This is the idea behind differential replication of machine learning models.