arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1702.02519cs.LGcs.AIstat.ML
收藏

深度广义典型相关分析

Deep Generalized Canonical Correlation Analysis

Johns Hopkins University(约翰斯·霍普金斯大学)

Adrian Benton, Huda Khayrallah, Biman Gujral, Dee Ann Reisinger, Sheng Zhang, Raman Arora

摘要:

我们提出了深度广义典型相关分析(DGCCA)--一种学习任意多个数据视图的非线性变换的方法,使得所得到的变换最大限度地相互提供信息。虽然用于非线性双视图表示学习的方法(Deep CCA,(Andrew等人,2013))和线性多视图表示学习(广义CCA(Horst,1961))的情况下,DGCCA是第一种CCA式多视图表示学习技术,其将非线性(深度)表示学习的灵活性与合并来自许多独立源或视图的信息的统计能力相结合。我们提出了DGCCA制定以及一个有效的随机优化算法来解决它。我们学习DGCCA表示在两个不同的数据集上的三个下游任务:从声学和发音测量的语音转录,并推荐Twitter用户的数据集上的标签和朋友。我们发现,DGCCA表示在音标和主题标签推荐方面完全击败了现有方法,并且一般来说表现不比标准线性多视图技术差。

英文摘要:

We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other. While methods for nonlinear two-view representation learning (Deep CCA, (Andrew et al., 2013)) and linear many-view representation learning (Generalized CCA (Horst, 1961)) exist, DGCCA is the first CCA-style multiview representation learning technique that combines the flexibility of nonlinear (deep) representation learning with the statistical power of incorporating information from many independent sources, or views. We present the DGCCA formulation as well as an efficient stochastic optimization algorithm for solving it. We learn DGCCA representations on two distinct datasets for three downstream tasks: phonetic transcription from acoustic and articulatory measurements, and recommending hashtags and friends on a dataset of Twitter users. We find that DGCCA representations soundly beat existing methods at phonetic transcription and hashtag recommendation, and in general perform no worse than standard linear many-view techniques.

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。

↑