用模型内部状态指导排序模型优化，减少试错成本。
MISO: Model-Internal-State-Guided Optimization for Ranking Models
- 基于参数、激活等内部状态生成优化信号
- 广告排序任务中降低验证次数，提升归一化熵
- 适合需要持续调优的工业级排序系统
排序模型在既定模型家族中反复迭代优化，但组件扩容、替换或淘汰的选择常依赖昂贵的试错。本文提出模型内部状态优化（MISO），利用模型内部状态（包括参数、激活、梯度和归一化统计量）来优先决策局部优化。MISO从训练好的排序模型中提取内部状态，聚合为排序、对齐和比较信号，并转化为少量可解释的候选修改。由于每次重训练后都会重新提取内部状态，MISO自然支持适应性优化流程，能跟踪数据分布和系统需求随时间变化的模型行为。在广告排序案例研究中，MISO在显著减少验证次数的同时提升了归一化熵，为人工调优与黑盒自动化搜索之间提供了实用折衷方案。
原文摘要 · Abstract (English)
Ranking models are repeatedly refined within established model families, yet the choice of which component to scale, replace, or retire is often guided by expensive trial-and-error. We present Model Internal State Optimization (MISO), a systems workflow that uses model internal states (MIS), including parameters, activations, gradients, and normalization statistics, to prioritize such local optimization decisions. MISO extracts MIS from a trained ranking model, aggregates them into ranking, alignment, and comparison signals, and converts those signals into a small set of interpretable candidate edits. Because MIS are re-extracted after each retraining cycle, MISO naturally supports an adaptive optimization workflow that tracks evolving model behavior as data distributions and system requirements shift over time. In an ads ranking case study, MISO improves normalized entropy while requiring substantially fewer validation runs than expert-driven and black-box scaling workflows, offering a practical middle ground between manual tuning and opaque automated search.
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。