arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.11776cs.LGcs.DC
收藏

MUSE:多租户模型服务与无缝模型更新

MUSE: Multi-Tenant Model Serving With Seamless Model Updates

Feedzai Portugal(Feedzai葡萄牙公司)

Cláudio Correia, Alberto E. A. Ferreira, Lucas Martins, Miguel P. Bento, Sofia Guerreiro, Ricardo Ribeiro Pereira, Ana Sofia Gomes, Jacopo Bono, Hugo Ferreira, Pedro Bizarro

AI总结:

MUSE通过解耦模型得分与客户端决策边界,实现了多租户环境下无缝模型更新,提升了模型的适应性和效率。

摘要:

在二分类系统中,决策阈值将模型得分转化为动作。选择合适的阈值依赖于底层模型得分的分布,也取决于使用该模型的每个客户端的具体业务决策。然而,重新训练模型不可避免地会改变得分分布,从而使现有阈值失效。在多租户Score-as-a-Service环境中,决策边界位于客户端管理的基础设施中,这会创建一个严重的瓶颈:重新校准需要在数百个客户端之间协调阈值更新,消耗大量的人力小时,导致模型停滞。我们介绍了MUSE,一种模型服务框架,通过将模型得分与客户端决策边界解耦,实现了无缝的模型更新。MUSE专为多租户设计,通过动态意图基于路由共享模型,结合两级得分转换,将模型输出映射到稳定的参考分布。由Feedzai大规模部署,MUSE每秒处理超过千个事件,过去12个月处理了550亿个事件,覆盖几十个租户,同时保持高可用性和低延迟保障。通过将模型准备时间从周缩短到分钟,MUSE增强了模型对变化攻击的抵抗力,节省了数百万美元的欺诈损失和运营成本。

英文摘要:

In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of the underlying model scores but also on the specific business decisions of each client using that model. However, retraining models inevitably shifts score distributions, invalidating existing thresholds. In multi-tenant Score-as-a-Service environments, where decision boundaries reside in client-managed infrastructure, this creates a severe bottleneck: recalibration requires coordinating threshold updates across hundreds of clients, consuming excessive human hours and leading to model stagnation. We introduce MUSE, a model serving framework that enables seamless model updates by decoupling model scores from client decision boundaries. Designed for multi-tenancy, MUSE optimizes infrastructure re-use by sharing models via dynamic intent-based routing, combined with a two-level score transformation that maps model outputs to a stable, reference distribution. Deployed at scale by Feedzai, MUSE processes over 4 thousand events per second, and over 55 billion events in the last 12 months, across several dozens of tenants, while maintaining high-availability and low-latency guarantees. By reducing model lead time from weeks to minutes, MUSE promotes model resilience against shifting attacks, saving millions of dollars in fraud losses and operational costs.

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。

↑