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 1709.05976cs.LGcs.AI
收藏

利用分布式语义进行多标签学习

Leveraging Distributional Semantics for Multi-Label Learning

IIT Kanpur(印度理工学院坎普尔分校);Microsoft Research(微软研究院)

Rahul Wadbude, Vivek Gupta, Piyush Rai, Nagarajan Natarajan, Harish Karnick, Prateek Jain

摘要:

我们提出了一种新的和可扩展的标签嵌入框架,用于大规模的多标签学习a. k. aExMLDS(使用分布式语义的极端多标签学习)。我们的方法从分布式语义中汲取灵感,特别是跳过革兰氏阴性采样(SGNS)方法,广泛用于学习自然语言处理任务的词嵌入。学习这样的嵌入可以简化为某种矩阵分解。我们的方法是新颖的,因为它突出了用于多标签学习的标签嵌入方法和通常用于学习文本数据表示的段落/文档嵌入方法之间的有趣联系。该框架也可以很容易地扩展到包含辅助信息,如标签-标签相关性;这是至关重要的,特别是当训练数据中有很多缺失的标签时。我们通过在各种基准数据集上进行的大量实验证明了我们方法的有效性,并表明与几种基线和最先进的大规模多标签学习方法相比,所提出的学习方法表现良好。为了促进端到端的学习,我们开发了一个联合学习算法,可以学习嵌入以及回归模型,预测这些嵌入给定的输入功能,通过有效的基于梯度的方法。

英文摘要:

We present a novel and scalable label embedding framework for large-scale multi-label learning a.k.a ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our approach draws inspiration from ideas rooted in distributional semantics, specifically the Skip Gram Negative Sampling (SGNS) approach, widely used to learn word embeddings for natural language processing tasks. Learning such embeddings can be reduced to a certain matrix factorization. Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and paragraph/document embedding methods commonly used for learning representations of text data. The framework can also be easily extended to incorporate auxiliary information such as label-label correlations; this is crucial especially when there are a lot of missing labels in the training data. We demonstrate the effectiveness of our approach through an extensive set of experiments on a variety of benchmark datasets, and show that the proposed learning methods perform favorably compared to several baselines and state-of-the-art methods for large-scale multi-label learning. To facilitate end-to-end learning, we develop a joint learning algorithm that can learn the embeddings as well as a regression model that predicts these embeddings given input features, via efficient gradient-based methods.

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。

↑