0


基于深度度量学习的高效相似区域搜索

Efficient Similar Region Search with Deep Metric Learning
课程网址: http://videolectures.net/kdd2018_liu_efficient_region/  
主讲教师: Yiding Liu
开课单位: 南洋理工大学
开课时间: 2018-11-23
课程语种: 英语
中文简介:
随着移动设备和基于位置的服务的普及,丰富的地理标记数据正在变得流行,这为了解不同的地理区域(例如,购物区)提供了巨大的机会。然而,大量具有复杂空间信息的区域对人们来说是昂贵的探索和理解。为了解决这个问题,我们研究了在给定用户指定的查询区域的情况下搜索相似区域的问题。该问题在相似性定义和搜索效率方面都具有挑战性。为了应对这两个挑战,我们提出了一种新的解决方案,该解决方案配备了(1)一种深度学习方法来学习相似度,该方法同时考虑了对象属性和对象之间的相对位置;以及(2)用于查找前N个相似区域的有效分支和边界搜索算法。此外,我们提出了一种近似方法,通过略微牺牲精度来进一步提高效率。我们在三个真实世界数据集上的实验表明,与最先进的方法相比,我们的解决方案显著提高了准确性和搜索效率。
课程简介: With the proliferation of mobile devices and location-based services, rich geo-tagged data is becoming prevalent and this offer great opportunities to understand different geographical regions (e.g., shopping areas). However, the huge number of regions with complicated spatial information are expensive for people to explore and understand. To solve this issue, we study the problem of searching similar regions given a user specified query region. The problem is challenging in both similarity definition and search efficiency. To tackle the two challenges, we propose a novel solution equipped by (1) a deep learning approach to learning the similarity that considers both object attributes and the relative locations between objects; and (2) an efficient branch and bound search algorithm for finding top-N similar regions. Moreover, we propose an approximation method to further improve the efficiency by slightly sacrificing the accuracy. Our experiments on three real world datasets demonstrate that our solution improves both the accuracy and search efficiency by a significant margin compared with the state-of-the-art methods.
关 键 词: 地理标记; 复杂空间; 搜索效率
课程来源: 视频讲座网
数据采集: 2022-12-19:chenjy
最后编审: 2023-05-11:chenjy
阅读次数: 29