arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07335cs.IRcs.AIcs.DC
收藏

面向序列推荐的智能模型更新策略

Intelligent Model Update Strategy for Sequential Recommendation

Zhejiang University(浙江大学)

Zheqi Lv, Wenqiao Zhang, Zhengyu Chen, Shengyu Zhang, Kun Kuang

AI总结:

针对边云协同序列推荐中频繁参数更新造成的资源浪费,本文提出边缘侧 IntellectReq,通过分布外检测、统计映射与不确定性量化自适应决定参数请求,显著提升效率与泛化性。

摘要:

现代在线平台越来越多地采用推荐系统来应对信息过载并提升用户参与度。该研究领域正在形成一种不断演进的范式:推荐网络学习同时发生在云端和边缘,并在二者之间进行知识迁移(即边云协同)。近期工作通过支持边缘特定的情境感知自适应进一步推动了该领域发展,即根据到达边缘的数据实时更新模型参数。然而,我们认为云与边缘之间频繁的数据交换往往导致低效以及通信/计算资源浪费,因为大量参数更新可能是冗余的。为研究这一问题,我们提出了 Intelligent Edge-Cloud Parameter Request Model(智能边云参数请求模型),缩写为 IntellectReq。IntellectReq 被设计为在边缘运行,以最小的计算和通信开销评估参数请求的成本—收益状况。我们将此构建为一种新的学习任务,旨在检测分布外数据,从而微调自适应通信策略。此外,我们采用统计映射技术将实时用户行为转换为正态分布,进而利用多样本输出量化模型的不确定性及其泛化能力。在四个广泛采用的基准上进行的严格实证验证评估了我们的方法,结果表明边云协同与动态推荐系统在效率和泛化性方面均有显著提升。

英文摘要:

Modern online platforms are increasingly employing recommendation systems to address information overload and improve user engagement. There is an evolving paradigm in this research field that recommendation network learning occurs both on the cloud and on edges with knowledge transfer in between (i.e., edge-cloud collaboration). Recent works push this field further by enabling edge-specific context-aware adaptivity, where model parameters are updated in real-time based on incoming on-edge data. However, we argue that frequent data exchanges between the cloud and edges often lead to inefficiency and waste of communication/computation resources, as considerable parameter updates might be redundant. To investigate this problem, we introduce Intelligent Edge-Cloud Parameter Request Model, abbreviated as IntellectReq. IntellectReq is designed to operate on edge, evaluating the cost-benefit landscape of parameter requests with minimal computation and communication overhead. We formulate this as a novel learning task, aimed at the detection of out-of-distribution data, thereby fine-tuning adaptive communication strategies. Further, we employ statistical mapping techniques to convert real-time user behavior into a normal distribution, thereby employing multi-sample outputs to quantify the model's uncertainty and thus its generalization capabilities. Rigorous empirical validation on four widely-adopted benchmarks evaluates our approach, evidencing a marked improvement in the efficiency and generalizability of edge-cloud collaborative and dynamic recommendation 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。

↑