arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.03215cs.LGcs.AIcs.CRcs.SI
收藏

用于跨设备用户匹配的带交叉注意力机制的层次图神经网络

Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching

NVIDIA(英伟达);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Ali Taghibakhshi, Mingyuan Ma, Ashwath Aithal, Onur Yilmaz, Haggai Maron, Matthew West

AI总结:

针对跨设备用户匹配中难以处理日志间长程依赖和高阶连接的问题,提出层次图神经网络(HGNN)和交叉注意力机制,计算效率优于TGCE且性能提升5%。

摘要:

跨设备用户匹配是广告、推荐系统和网络安全等众多领域的关键问题。它利用序列日志识别并链接属于同一个人的不同设备。以往的数据挖掘技术难以处理日志间的长程依赖和高阶连接。最近,研究人员将该问题建模为图问题,并提出了两层图上下文嵌入(TGCE)神经网络架构,其性能优于以往方法。本文提出了一种新颖的层次图神经网络架构(HGNN),其第二级设计比TGCE更具计算效率。此外,我们在模型中引入了交叉注意力(Cross-Att)机制,与最先进的TGCE方法相比,性能提升了5%。

英文摘要:

Cross-device user matching is a critical problem in numerous domains, including advertising, recommender systems, and cybersecurity. It involves identifying and linking different devices belonging to the same person, utilizing sequence logs. Previous data mining techniques have struggled to address the long-range dependencies and higher-order connections between the logs. Recently, researchers have modeled this problem as a graph problem and proposed a two-tier graph contextual embedding (TGCE) neural network architecture, which outperforms previous methods. In this paper, we propose a novel hierarchical graph neural network architecture (HGNN), which has a more computationally efficient second level design than TGCE. Furthermore, we introduce a cross-attention (Cross-Att) mechanism in our model, which improves performance by 5% compared to the state-of-the-art TGCE method.

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。

↑