arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.02173cs.IRcs.LG
收藏

效率与准确性的权衡:使用多头早期退出优化RAG增强的LLM推荐系统

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit

Meta Platforms(Meta平台);University of Minnesota(明尼苏达大学);NCSU(北卡罗来纳州立大学);UNC at Chapel Hill(Chapel Hill分校,北卡罗来纳大学)
Huixue Zhou, Hengrui Gu, Xi Liu, Kaixiong Zhou, Mingfu Liang, Yongkang Xiao, Srinivas Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang,… 展开作者

Huixue Zhou, Hengrui Gu, Xi Liu, Kaixiong Zhou, Mingfu Liang, Yongkang Xiao, Srinivas Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

AI总结:

提出结合检索增强生成(RAG)与多头早期退出架构的优化框架,通过图卷积网络(GCN)高效检索和动态推理终止,在降低计算时间的同时保持或提升点击率(CTR)预测准确性。

摘要:

在推荐系统中部署大型语言模型(LLM)以预测点击率(CTR)需要在计算效率和预测准确性之间取得微妙的平衡。本文提出一个优化框架,结合检索增强生成(RAG)与创新的多头早期退出架构,同时增强这两个方面。通过集成图卷积网络(GCN)作为高效检索机制,我们能够显著减少数据检索时间,同时保持高模型性能。采用的早期退出策略允许动态终止模型推理,利用跨多个头的实时预测置信度评估。这不仅加快了LLM的响应速度,还维持或提高了其准确性,使其非常适合实时应用场景。我们的实验表明,该架构有效减少了计算时间,而不牺牲可靠推荐交付所需的准确性,为商业系统中高效、实时的LLM部署建立了新标准。

英文摘要:

The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy. This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture to concurrently enhance both aspects. By integrating Graph Convolutional Networks (GCNs) as efficient retrieval mechanisms, we are able to significantly reduce data retrieval times while maintaining high model performance. The early exit strategy employed allows for dynamic termination of model inference, utilizing real-time predictive confidence assessments across multiple heads. This not only quickens the responsiveness of LLMs but also upholds or improves their accuracy, making it ideal for real-time application scenarios. Our experiments demonstrate how this architecture effectively decreases computation time without sacrificing the accuracy needed for reliable recommendation delivery, establishing a new standard for efficient, real-time LLM deployment in commercial systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑