无需重训即可弹性调整特征，加速大规模推荐系统迭代
Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale
- 在推理时动态控制特征覆盖范围与分布，避免模型重训
- 线上实验显示渐进式特征衰减可减少50%-55%性能下降
- 适合需要快速迭代、资源受限的工业级排序系统
大规模排序系统依赖来自多时间维度用户行为的数千个特征。传统方法需模型重训，导致迭代周期长达3-6个月，消耗大量GPU资源且部署吞吐量低。本文提出智能弹性特征衰减（IEFF），一种生产级基础设施系统，通过在推理时弹性调控特征覆盖率与分布，实现免重训的特征效率上线。该系统支持增量调整特征覆盖，同时模型通过持续训练自适应，消除对显式重训周期的依赖。系统内置严格安全防护、可逆机制和全面监控，保障大规模稳定性。多个生产场景验证：效率类更新提速5倍，彻底消除重训带来的GPU开销，加速资源回收。离线与在线实验表明，渐进式特征衰减相比突然移除，可预防50%-55%的线上性能下降，同时保持模型行为稳定。结果确立了弹性、系统级特征衰减在现代工业排序系统中的实用性和可扩展性。
原文摘要 · Abstract (English)
Large-scale ranking systems depend on thousands of features derived from user behavior across multiple time horizons. Typically requires model retraining -- resulting in long iteration cycles (3--6 months), substantial GPU resource consumption, and limited rollout throughput. We introduce Intelligent Elastic Feature Fading (IEFF), a production infrastructure system that enables retrain-free feature efficiency rollouts by elastically controlling feature coverage and distribution at serving time. IEFF supports incremental feature coverage adjustments while models adapt through recurring training, eliminating dependencies on explicit retraining cycles. The system incorporates strict safety guardrails, reversibility mechanisms, and comprehensive monitoring to ensure stability at scale. Across multiple production use cases, IEFF accelerates efficiency-related rollouts by 5$\times$, eliminates retraining-related GPU overhead, and enables faster capacity recycling. Extensive offline and online experiments demonstrate that gradual feature fading prevents 50--55\% of online performance degradation compared to abrupt feature removal, while maintaining stable model behavior. These results establish elastic, system-level feature fading as a practical and scalable approach for managing feature efficiency in modern industrial ranking systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。