arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02418cs.DBcs.AI
收藏

ML增强型DBMS的统一可迁移模型

A Unified Transferable Model for ML-Enhanced DBMS

Alibaba Group(阿里巴巴集团);Massachusetts Institute of Technology(麻省理工学院);University of Technology Sydney(悉尼科技大学);University of Science and Technology of China(中国科学技术大学)

Ziniu Wu, Pei Yu, Peilun Yang, Rong Zhu, Yuxing Han, Yaliang Li, Defu Lian, Kai Zeng, Jingren Zhou

摘要:

最近,数据库管理系统(DBMS)社区见证了用于DBMS任务的机器学习(ML)解决方案的强大功能。尽管这些现有的解决方案具有良好的性能,但很难被认为是令人满意的。首先,DBMS中这些基于ML的方法不够有效,因为它们针对每个特定任务进行了优化,并且无法探索或理解任务之间的内在联系。其次,训练过程有严重的局限性,这阻碍了它们的实用性,因为它们需要从头开始重新训练整个模型以获得新的数据库。此外,对于每次再训练,它们需要过量的训练数据,这对于获取是非常昂贵的并且对于新DB是不可用的。我们建议探索ML方法在任务和DB之间的可转移性,以解决这些基本缺陷。在本文中,我们提出了一个统一的模型MTMLF,它使用多任务训练过程来捕获跨任务的可转移知识和预训练微调过程来提取跨数据库的可转移Meta知识。我们相信这种范式更适合云数据库服务,并有可能彻底改变ML在DBMS中的使用方式。此外,为了证明MTMLF的预测能力和可行性,我们提供了一个具体的和非常有前途的案例研究查询优化任务。最后但并非最不重要的是,我们讨论了沿着这条工作线的几个具体的研究机会。

英文摘要:

Recently, the database management system (DBMS) community has witnessed the power of machine learning (ML) solutions for DBMS tasks. Despite their promising performance, these existing solutions can hardly be considered satisfactory. First, these ML-based methods in DBMS are not effective enough because they are optimized on each specific task, and cannot explore or understand the intrinsic connections between tasks. Second, the training process has serious limitations that hinder their practicality, because they need to retrain the entire model from scratch for a new DB. Moreover, for each retraining, they require an excessive amount of training data, which is very expensive to acquire and unavailable for a new DB. We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks. In this paper, we propose a unified model MTMLF that uses a multi-task training procedure to capture the transferable knowledge across tasks and a pre-train fine-tune procedure to distill the transferable meta knowledge across DBs. We believe this paradigm is more suitable for cloud DB service, and has the potential to revolutionize the way how ML is used in DBMS. Furthermore, to demonstrate the predicting power and viability of MTMLF, we provide a concrete and very promising case study on query optimization tasks. Last but not least, we discuss several concrete research opportunities along this line of work.

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。

↑