CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models

arXiv:2312.03256v2 Announce Type: replace
Abstract: Recently, the growing memory demands of embedding tables in Deep Learning Recommendation Models (DLRMs) pose great challenges for model training and deployment. Existing embedding compression solutions cannot simultaneously meet three key design requirements: memory efficiency, low latency, and adaptability to dynamic data distribution. This paper presents CAFE, a Compact, Adaptive, and Fast Embedding compression framework that addresses the above requirements. The design philosophy of CAFE is to dynamically allocate more memory resources to important features …

abstract adaptability arxiv challenges compact compression cs.lg data deep learning deployment design distribution dynamic efficiency embedding key latency low low latency memory recommendation requirements scale solutions tables training type