Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems

arXiv:2404.14961v1 Announce Type: new
Abstract: Modern large-scale recommender systems are built upon computation-intensive infrastructure and usually suffer from a huge difference in traffic between peak and off-peak periods. In peak periods, it is challenging to perform real-time computation for each request due to the limited budget of computational resources. The recommendation with a cache is a solution to this problem, where a user-wise result cache is used to provide recommendations when the recommender system cannot afford a real-time computation. However, …

abstract arxiv budget cache computation computational cs.lg difference infrastructure modern peak real-time recommendation recommender systems reinforcement reinforcement learning request resources scale systems traffic type