HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps

Jizhou Huang, Haifeng Wang, Yibo Sun, Miao Fan, Zhengjie Huang, Chunyuan Yuan, Yawen Li
{"title":"HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps","authors":"Jizhou Huang, Haifeng Wang, Yibo Sun, Miao Fan, Zhengjie Huang, Chunyuan Yuan, Yawen Li","doi":"arxiv-2409.03504","DOIUrl":null,"url":null,"abstract":"The increasing interest in international travel has raised the demand of\nretrieving point of interests in multiple languages. This is even superior to\nfind local venues such as restaurants and scenic spots in unfamiliar languages\nwhen traveling abroad. Multilingual POI retrieval, enabling users to find\ndesired POIs in a demanded language using queries in numerous languages, has\nbecome an indispensable feature of today's global map applications such as\nBaidu Maps. This task is non-trivial because of two key challenges: (1)\nvisiting sparsity and (2) multilingual query-POI matching. To this end, we\npropose a Heterogeneous Graph Attention Matching Network (HGAMN) to\nconcurrently address both challenges. Specifically, we construct a\nheterogeneous graph that contains two types of nodes: POI node and query node\nusing the search logs of Baidu Maps. To alleviate challenge \\#1, we construct\nedges between different POI nodes to link the low-frequency POIs with the\nhigh-frequency ones, which enables the transfer of knowledge from the latter to\nthe former. To mitigate challenge \\#2, we construct edges between POI and query\nnodes based on the co-occurrences between queries and POIs, where queries in\ndifferent languages and formulations can be aggregated for individual POIs.\nMoreover, we develop an attention-based network to jointly learn node\nrepresentations of the heterogeneous graph and further design a cross-attention\nmodule to fuse the representations of both types of nodes for query-POI\nrelevance scoring. Extensive experiments conducted on large-scale real-world\ndatasets from Baidu Maps demonstrate the superiority and effectiveness of\nHGAMN. In addition, HGAMN has already been deployed in production at Baidu\nMaps, and it successfully keeps serving hundreds of millions of requests every\nday.","PeriodicalId":501281,"journal":{"name":"arXiv - CS - Information Retrieval","volume":"2 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.03504","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The increasing interest in international travel has raised the demand of retrieving point of interests in multiple languages. This is even superior to find local venues such as restaurants and scenic spots in unfamiliar languages when traveling abroad. Multilingual POI retrieval, enabling users to find desired POIs in a demanded language using queries in numerous languages, has become an indispensable feature of today's global map applications such as Baidu Maps. This task is non-trivial because of two key challenges: (1) visiting sparsity and (2) multilingual query-POI matching. To this end, we propose a Heterogeneous Graph Attention Matching Network (HGAMN) to concurrently address both challenges. Specifically, we construct a heterogeneous graph that contains two types of nodes: POI node and query node using the search logs of Baidu Maps. To alleviate challenge \#1, we construct edges between different POI nodes to link the low-frequency POIs with the high-frequency ones, which enables the transfer of knowledge from the latter to the former. To mitigate challenge \#2, we construct edges between POI and query nodes based on the co-occurrences between queries and POIs, where queries in different languages and formulations can be aggregated for individual POIs. Moreover, we develop an attention-based network to jointly learn node representations of the heterogeneous graph and further design a cross-attention module to fuse the representations of both types of nodes for query-POI relevance scoring. Extensive experiments conducted on large-scale real-world datasets from Baidu Maps demonstrate the superiority and effectiveness of HGAMN. In addition, HGAMN has already been deployed in production at Baidu Maps, and it successfully keeps serving hundreds of millions of requests every day.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
HGAMN:用于百度地图多语言 POI 检索的异构图注意力匹配网络
人们对国际旅行的兴趣与日俱增,这就提出了用多种语言检索兴趣点的要求。在国外旅行时,用陌生语言查找当地的餐馆和风景名胜等场所甚至更有优势。多语种兴趣点检索使用户能够使用多种语言查询找到所需语言的兴趣点,已成为当今全球地图应用程序(如百度地图)不可或缺的功能。这项任务并非易事,因为它面临两个关键挑战:(1) 访问稀疏性;(2) 多语言查询-POI 匹配。为此,我们提出了异构图注意力匹配网络(HGAMN)来同时应对这两个挑战。具体来说,我们构建了一个包含两类节点的异构图:POI 节点和查询节点。为了缓解挑战#1,我们在不同 POI 节点之间构建了节点,将低频 POI 与高频 POI 连接起来,从而实现了从后者到前者的知识转移。此外,我们还开发了一种基于注意力的网络来共同学习异构图的节点表示,并进一步设计了一种交叉注意力模块来融合两种类型节点的表示,从而实现查询-POI相关性评分。在百度地图的大规模真实数据集上进行的广泛实验证明了 HGAMN 的优越性和有效性。此外,HGAMN 已经部署在百度地图的生产环境中,并成功地为每天数以亿计的请求提供服务。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Decoding Style: Efficient Fine-Tuning of LLMs for Image-Guided Outfit Recommendation with Preference Retrieve, Annotate, Evaluate, Repeat: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation Active Reconfigurable Intelligent Surface Empowered Synthetic Aperture Radar Imaging FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement Basket-Enhanced Heterogenous Hypergraph for Price-Sensitive Next Basket Recommendation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1