Modular Representation Compression: Adapting LLM Representations for Efficient and Effective Recommendation
Yunjia Xi · Menghui Zhu (Huawei Noah' · Ruiming Tang (Huawei Noah' · Ruiming Tang (Huawei Noah' · Ruiming Tang (Huawei Noah' · s Ark Lab) · Ruiming Tang (Huawei Noah' · Ruiming Tang (Huawei Noah' · s Ark Lab) · Ruiming Tang (Huawei Noah'
摘要
Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache augmented representations for RSs, high-dimensional representati...