arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.14703stat.MLcs.LG
收藏

结构化预测中的学习输出嵌入

Learning Output Embeddings in Structured Prediction

LTCI, Télécom Paris, IP Paris(LTCI,巴黎电信,巴黎理工学院);INRIA - Département d’Informatique de l’ENS, PSL(法国国家信息与自动化研究所 - 巴黎高等师范学院计算机系,巴黎文理研究大学);INRAE, MIAT, Université de Toulouse(法国国家农业食品与环境研究院,图卢兹大学);Department of Computer Science, Aalto University(阿尔托大学计算机科学系)

Luc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu, Florence d'Alché-Buc

摘要:

结构化预测的一种强大而灵活的方法在于通过输出核将待预测的结构化对象嵌入到可能无限维的特征空间中,然后在该输出空间中解决回归问题。通过求解前像问题来计算原始空间中的预测。在这种方法中,与目标损失相关联的嵌入在学习阶段之前被定义。在这项工作中,我们建议共同学习输出嵌入和回归函数到新的特征空间的有限近似。为此,我们利用了输出的先验信息以及未利用的无监督输出数据,这两者在结构化预测问题中经常可用。我们证明了由此产生的结构化预测器是一个相合估计量,并推导出超额风险界。此外,新的结构化预测工具享有一个显着较小的计算复杂度比以前的输出核方法。在各种结构化预测问题上进行的经验测试表明,该方法是通用的,能够处理大型数据集。

英文摘要:

A powerful and flexible approach to structured prediction consists in embedding the structured objects to be predicted into a feature space of possibly infinite dimension by means of output kernels, and then, solving a regression problem in this output space. A prediction in the original space is computed by solving a pre-image problem. In such an approach, the embedding, linked to the target loss, is defined prior to the learning phase. In this work, we propose to jointly learn a finite approximation of the output embedding and the regression function into the new feature space. For that purpose, we leverage a priori information on the outputs and also unexploited unsupervised output data, which are both often available in structured prediction problems. We prove that the resulting structured predictor is a consistent estimator, and derive an excess risk bound. Moreover, the novel structured prediction tool enjoys a significantly smaller computational complexity than former output kernel methods. The approach empirically tested on various structured prediction problems reveals to be versatile and able to handle large 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。

↑