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 1810.03463stat.MLcs.LG
收藏

基于移位内积相似的图嵌入及其改进的逼近能力

Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability

Kyoto University(京都大学);RIKEN Center for Artificial Intelligence Project(理化学研究所人工智能项目中心)

Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira

摘要:

我们提出了移位内积相似性(SIPS),这是一个新的但非常简单的扩展普通的内积相似性(IPS)的基于神经网络的图嵌入(GE)。与IPS仅限于近似正定(PD)相似性相比,SIPS通过引入偏置项超越了IPS的局限性,并通过余弦相似性、负Poincare距离和负瓦瑟斯坦距离等实例证明了SIPS不仅能够近似PD,而且能够近似条件PD(CPD)相似性.由于具有足够大的神经网络的SIPS学习各种相似性,SIPS消除了配置GE的相似性函数的需要。近似误差率也进行了评估,并在两个真实世界的数据集上的实验表明,使用SIPS的图嵌入确实优于现有的方法。

英文摘要:

We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embedding (GE). In contrast to IPS, that is limited to approximating positive-definite (PD) similarities, SIPS goes beyond the limitation by introducing bias terms in IPS; we theoretically prove that SIPS is capable of approximating not only PD but also conditionally PD (CPD) similarities with many examples such as cosine similarity, negative Poincare distance and negative Wasserstein distance. Since SIPS with sufficiently large neural networks learns a variety of similarities, SIPS alleviates the need for configuring the similarity function of GE. Approximation error rate is also evaluated, and experiments on two real-world datasets demonstrate that graph embedding using SIPS indeed outperforms existing 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。

↑