arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.01449cs.IRcs.DBcs.DScs.PF
收藏

索引还是不索引:最优化精确最大内积搜索

To Index or Not to Index: Optimizing Exact Maximum Inner Product Search

Firas Abuzaid, Geet Sethi, Peter Bailis, Matei Zaharia

摘要:

精确最大内积搜索(MIPS)是推荐系统和高维相似性搜索中的一个重要研究课题。解决精确MIPS的蛮力方法在计算上是昂贵的,因此刺激了最近开发的新索引和修剪技术。在本文中,我们证明了一种硬件高效的蛮力方法,分块矩阵乘法(BMM),可以超过一个数量级的最先进的MIPS求解器,对于一些-但不是所有-输入。在本文中,我们还提出了一种新的MIPS解决方案,MAXIMUS,利用硬件效率和修剪的搜索空间。与BMM一样,MAXIMUS比其他求解器快一个数量级,但同样仅适用于某些输入。由于没有一个单一的解决方案提供最佳的运行时性能的所有输入,我们引入了一个新的数据依赖的优化器,OPTIMUS,选择最好的MIPS求解器为给定的输入在线以最小的开销。在广泛研究的MIPS数据集上,OPTIMUS和MAXIMUS的平均性能超过最先进的MIPS求解器3.2 $\times$,最高可达10.9 $\times$。

英文摘要:

Exact Maximum Inner Product Search (MIPS) is an important task that is widely pertinent to recommender systems and high-dimensional similarity search. The brute-force approach to solving exact MIPS is computationally expensive, thus spurring recent development of novel indexes and pruning techniques for this task. In this paper, we show that a hardware-efficient brute-force approach, blocked matrix multiply (BMM), can outperform the state-of-the-art MIPS solvers by over an order of magnitude, for some -- but not all -- inputs. In this paper, we also present a novel MIPS solution, MAXIMUS, that takes advantage of hardware efficiency and pruning of the search space. Like BMM, MAXIMUS is faster than other solvers by up to an order of magnitude, but again only for some inputs. Since no single solution offers the best runtime performance for all inputs, we introduce a new data-dependent optimizer, OPTIMUS, that selects online with minimal overhead the best MIPS solver for a given input. Together, OPTIMUS and MAXIMUS outperform state-of-the-art MIPS solvers by 3.2$\times$ on average, and up to 10.9$\times$, on widely studied MIPS datasets.

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。

↑