一作SIGIR 2026Poster· Information Retrieval (Industry)
Full Retraining, Incremental Fine-tuning, and Hybrid Serving: Model Updating and Serving for Industrial Generative Recommender Systems
Lu Fan · Qijiong Liu · Zhongzhou Liu · Guoyuan An · Wei Guo · Yong Liu · Xiao-Ming Wu
摘要
Generative recommendation casts recommendation as conditional sequence generation over text- or token-based representations and has shown strong promise in industrial systems. However, keeping such models up to date in dynamic environments is difficult: full retraining on sliding windows is expen...