Incremental Learning for Personalized Recommender Systems
This work addresses the problem of efficient model updates for personalized recommender systems in dynamic environments, representing an incremental improvement with practical deployment.
The paper tackles the challenge of balancing high-quality personalized recommendations with efficient model updates in recommender systems by introducing an incremental learning solution based on sequential Bayesian update and quadratic approximation. It demonstrates that this approach significantly shortens training time while maintaining model accuracy, as shown in offline and online experiments, and is deployed at LinkedIn for industrial-scale use.
Ubiquitous personalized recommender systems are built to achieve two seemingly conflicting goals, to serve high quality content tailored to individual user's taste and to adapt quickly to the ever changing environment. The former requires a complex machine learning model that is trained on a large amount of data; the latter requires frequent update to the model. We present an incremental learning solution to provide both the training efficiency and the model quality. Our solution is based on sequential Bayesian update and quadratic approximation. Our focus is on large-scale personalized logistic regression models, with extensions to deep learning models. This paper fills in the gap between the theory and the practice by addressing a few implementation challenges that arise when applying incremental learning to large personalized recommender systems. Detailed offline and online experiments demonstrated our approach can significantly shorten the training time while maintaining the model accuracy. The solution is deployed in LinkedIn and directly applicable to industrial scale recommender systems.