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 2108.00261cs.CLcs.IRcs.LG
收藏

ECLARE:基于标号图相关性的极端分类

ECLARE: Extreme Classification with Label Graph Correlations

IIT Delhi(德里印度理工学院);UC San Diego(加州大学圣地亚哥分校);Microsoft Research(微软研究院);IIT Kanpur(坎普尔印度理工学院)

Anshul Mittal, Noveen Sachdeva, Sheshansh Agrawal, Sumeet Agarwal, Purushottam Kar, Manik Varma

摘要:

深度极端分类(XC)旨在训练深度架构,这些架构可以使用极大标签集中最相关的标签子集来标记数据点。XC的核心效用来自于预测训练过程中很少看到的标签。这种罕见的标签是个性化推荐的关键,可以让用户感到高兴和惊讶。然而,大量的稀有标签和每个稀有标签的少量训练数据提供了显著的统计和计算挑战。最先进的深度XC方法试图通过合并标签的文本描述来解决这个问题,但没有充分解决这个问题。本文介绍了ECLARE,这是一种可扩展的深度学习架构,不仅包含标签文本,还包含标签相关性,可在几毫秒内提供准确的实时预测。ECLARE的核心贡献包括一个简单的架构和可扩展的技术,以训练深度模型以及数百万标签规模的标签相关图。特别是,ECLARE提供的预测是2%至14%以上的准确性都公开可用的基准数据集,以及专有数据集的相关产品推荐任务来源于必应搜索引擎。ECLARE代码可在https://github.com/Extreme-classification/ECLARE上找到。

英文摘要:

Deep extreme classification (XC) seeks to train deep architectures that can tag a data point with its most relevant subset of labels from an extremely large label set. The core utility of XC comes from predicting labels that are rarely seen during training. Such rare labels hold the key to personalized recommendations that can delight and surprise a user. However, the large number of rare labels and small amount of training data per rare label offer significant statistical and computational challenges. State-of-the-art deep XC methods attempt to remedy this by incorporating textual descriptions of labels but do not adequately address the problem. This paper presents ECLARE, a scalable deep learning architecture that incorporates not only label text, but also label correlations, to offer accurate real-time predictions within a few milliseconds. Core contributions of ECLARE include a frugal architecture and scalable techniques to train deep models along with label correlation graphs at the scale of millions of labels. In particular, ECLARE offers predictions that are 2 to 14% more accurate on both publicly available benchmark datasets as well as proprietary datasets for a related products recommendation task sourced from the Bing search engine. Code for ECLARE is available at https://github.com/Extreme-classification/ECLARE.

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。

↑