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 2210.07768cs.IRcs.LG
收藏

FeatureBox:面向大规模广告系统的GPU特征工程

FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems

Baidu Research(百度研究院);Baidu Inc.(百度公司)

Weijie Zhao, Xuewu Jiao, Xinsheng Luo, Jingxue Li, Belhal Karimi, Ping Li

摘要:

深度学习已被广泛部署用于在线广告系统以预测点击率(CTR)。机器学习研究人员和从业者经常重新训练CTR模型,以测试他们新提取的特征。然而,CTR模型训练通常依赖于大量原始输入数据日志。因此,对于工业级CTR模型,特征提取可能占用很大比例的训练时间。在本文中,我们提出了一种新的端到端训练框架,它将特征提取和GPU服务器上的训练进行流水线化,以节省特征提取的中间I/O。我们将计算密集型特征提取运算符重写为GPU运算符,并将内存密集型运算符留在CPU上。我们引入了一个分层的运营商调度算法来调度这些异构运营商。我们提出了一种轻量级的GPU存储管理算法,支持动态GPU内存分配,以最小的开销。我们通过实验评估了MatureBox,并在两个真实的广告应用程序上将其与之前的生产特征提取框架进行了比较。实验结果证实了该方法的有效性。

英文摘要:

Deep learning has been widely deployed for online ads systems to predict Click-Through Rate (CTR). Machine learning researchers and practitioners frequently retrain CTR models to test their new extracted features. However, the CTR model training often relies on a large number of raw input data logs. Hence, the feature extraction can take a significant proportion of the training time for an industrial-level CTR model. In this paper, we propose FeatureBox, a novel end-to-end training framework that pipelines the feature extraction and the training on GPU servers to save the intermediate I/O of the feature extraction. We rewrite computation-intensive feature extraction operators as GPU operators and leave the memory-intensive operator on CPUs. We introduce a layer-wise operator scheduling algorithm to schedule these heterogeneous operators. We present a light-weight GPU memory management algorithm that supports dynamic GPU memory allocation with minimal overhead. We experimentally evaluate FeatureBox and compare it with the previous in-production feature extraction framework on two real-world ads applications. The results confirm the effectiveness of our proposed method.

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。

↑