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 1912.01666cs.LGstat.ML
收藏

有序嵌入算法的系统评价

Insights into Ordinal Embedding Algorithms: A Systematic Evaluation

University of Tübingen(图宾根大学)

Leena Chennuru Vankadara, Siavash Haghiri, Michael Lohaus, Faiz Ul Wahab, Ulrike von Luxburg

摘要:

序数嵌入的目的是找到一组抽象项目的欧几里得表示,只使用形式为“项目$i$更接近项目$j$还是项目$k$?".近年来,已经提出了许多算法来解决这个问题。然而,并不存在一个公平和彻底的评估,这些嵌入方法,因此有几个关键的问题仍然没有答案:哪些算法表现更好时,嵌入尺寸的限制或几个三元比较可用?哪一个随着样本量或维度的增加而更好地扩展?在我们的论文中,我们解决这些问题,并提供了第一个全面和系统的经验评估现有的算法,以及一个新的神经网络的方法。我们发现,简单的,相对未知的,非凸的方法始终优于所有其他算法,包括精心设计的方法,基于神经网络或地标的方法。这一发现可以解释我们的洞察力,许多非凸优化方法不受局部最优。我们的全面评估由我们的流行嵌入算法的统一库实现,这些算法利用GPU资源,可以快速准确地嵌入数百万个数据点。

英文摘要:

The objective of ordinal embedding is to find a Euclidean representation of a set of abstract items, using only answers to triplet comparisons of the form "Is item $i$ closer to the item $j$ or item $k$?". In recent years, numerous algorithms have been proposed to solve this problem. However, there does not exist a fair and thorough assessment of these embedding methods and therefore several key questions remain unanswered: Which algorithms perform better when the embedding dimension is constrained or few triplet comparisons are available? Which ones scale better with increasing sample size or dimension? In our paper, we address these questions and provide the first comprehensive and systematic empirical evaluation of existing algorithms as well as a new neural network approach. We find that simple, relatively unknown, non-convex methods consistently outperform all other algorithms, including elaborate approaches based on neural networks or landmark approaches. This finding can be explained by our insight that many of the non-convex optimization approaches do not suffer from local optima. Our comprehensive assessment is enabled by our unified library of popular embedding algorithms that leverages GPU resources and allows for fast and accurate embeddings of millions of data points.

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。

↑