arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.08962cs.IRcs.LGstat.ML
收藏

DVE:动态变分嵌入及其在推荐系统中的应用

DVE: Dynamic Variational Embeddings with Applications in Recommender Systems

Meimei Liu, Hongxia Yang

摘要:

嵌入是一种将高维特征映射到低维空间的有效技术,在链接预测、节点分类和自然语言处理等领域有着广泛的应用。目前的方法主要集中在静态数据,这通常会导致不满意的性能,在应用程序中,涉及随着时间的推移大的变化。如何动态地表征嵌入特征的变化在很大程度上仍然是未探索的。在本文中,我们介绍了一个动态变分嵌入(DVE)方法的序列感知数据的基础上,在递归神经网络的最新进展。DVE可以明确地同时模拟节点的内在性质和时间变化,这对于探索至关重要。我们进一步将DVE应用于序列感知推荐系统,并开发了一个端到端的链接预测神经架构。

英文摘要:

Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches mainly focus on static data, which usually lead to unsatisfactory performance in applications involving large changes over time. How to dynamically characterize the variation of the embedded features is still largely unexplored. In this paper, we introduce a dynamic variational embedding (DVE) approach for sequence-aware data based on recent advances in recurrent neural networks. DVE can model the node's intrinsic nature and temporal variation explicitly and simultaneously, which are crucial for exploration. We further apply DVE to sequence-aware recommender systems, and develop an end-to-end neural architecture for link prediction.

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。

↑