arXiv cs.AI· Vishnu Arun, Adam Obeng, Tianyou Wang, Zilin Ren, Mukuntha Narayanan Sundararaman, Han Wang, Shivin Thukral, Zhixiang Wang, Saurabh Vishwas Joshi, Darren Reger·· 6 天前AI 评分22
FORTE：工业推荐系统中特征评估与淘汰的生产框架
FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems
AI 导读
FORTE 是一个模型无关的生产框架，用于发现、验证和移除推荐系统中的特征，通过高效扰动实现每日特征评估，并用分组消融处理特征交互。在搜索相关性模型上，FORTE 生成 32、48、59 三个嵌套候选特征集，最终选定 48 个特征进行淘汰，移除该模型 43.3% 的特征。
正文 · 原文
Abstract:Production recommender systems have feature-lifecycle asymmetry: adding new features must produce gains on some metric, while feature removal must not regress any metric. In practice, feature deprecation is hard to prioritize as a feature can fail to be removed if it interacts with other features, its importance changes daily, it cannot be evaluated before production models change or data drift occurs, it is in contention for A/B test space with other launches, it causes regressions in an online A/B test, or it is consumed by multiple models that need to coordinate its deprecation. We present FORTE, a model-agnostic production framework for discovering, validating, and removing features. Its efficient perturbation implementation allows daily feature evaluation. To account for interactions, it evaluates candidate feature sets constructed from all the low-rank features through grouped ablation and its offline results are sufficiently predictive of online A/B tests to allow deprecations to proceed to online testing with confidence. Lineage tracing identifies all downstream consumer models to realize the full savings of removing a feature from the training set. We validate FORTE over 2 large-scale recommender systems and find that it identifies deprecable feature sets which do not cause online regressions, while the impact on efficiency depends on model characteristics. On a search-relevance model, FORTE resulted in 3 nested candidate sets of 32, 48, and 59 features. Online guardrails rejected the largest treatment. The 48-feature set was selected for deprecation, removing 43.3% of the model's features. On a large ranking model, FORTE identified 8 candidates for removal. Retraining and A/B testing confirmed no regression. Its launch reduced the trainable parameters by 29.9%, improved serving throughput by 19.8-25.5%, and reduced annual training costs by hundreds of thousands of dollars.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.13806 [cs.LG] |
| (or arXiv:2610.13806v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13806 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Vishnu Arun [view email]
[v1]
Fri, 9 Oct 2026 16:18:39 UTC (102 KB)
来源：arXiv cs.AI · arxiv.org