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

TL;DR

This paper introduces HGAMN, a novel heterogeneous graph attention network that improves multilingual POI retrieval by addressing data sparsity and query-POI matching challenges, demonstrating superior performance and real-world deployment at Baidu Maps.

Contribution

We propose HGAMN, a heterogeneous graph attention network that effectively handles multilingual POI retrieval challenges with innovative graph construction and attention mechanisms.

Findings

Outperforms existing methods on large-scale Baidu Maps datasets.

Successfully deployed in Baidu Maps, serving hundreds of millions of requests daily.

Effectively alleviates data sparsity and improves multilingual query-POI matching.

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.