LBSN2Vec++: Heterogeneous Hypergraph Embedding for Location-Based Social Networks

Abstract

Location-Based Social Networks (LBSNs) have been widely used as a primary data source for studying the impact of mobility and social relationships on each other. Traditional approaches manually define features to characterize users' mobility homophily and social proximity, and show that mobility and social features can help friendship and location prediction tasks, respectively. However, these hand-crafted features not only require tedious human efforts, but also are difficult to generalize. Against this background, we propose in this paper LBSN2Vec++, a heterogeneous hypergraph embedding approach designed specifically for LBSN data for automatic feature learning. Specifically, LBSN data intrinsically forms a heterogeneous hypergraph including both user-user homogeneous edges (friendships) and user-time-POI-semantic heterogeneous hyperedges (check-ins). Based on this hypergraph, we first propose a random-walk-with-stay scheme to jointly sample user check-ins and social relationships, and then learn node embeddings from the sampled (hyper)edges by not only preserving the n-wise node proximity captured by the hyperedges, but also considering embedding space transformation between node domains to fully grasp the complex structural characteristics of the LBSN heterogeneous hypergraph. Using real-world LBSN datasets collected in six cities all over the world, our extensive evaluation shows that LBSN2Vec++ significantly and consistently outperforms both state-of-the-art graph embedding techniques by up to 68% and the best-performing hand-crafted features in the literature by up to 70.14% on friendship and location prediction tasks.

Heterogeneous interventions reduce the spread of COVID-19 in simulations on real mobility data

“… Foursquare check-ins. We use check-in data 25 , 26 from the Foursquare mobile application, which captures snapshots of human mobility in popular public spaces. The dataset includes seven major cities across the world (New York, Chicago, Los Angeles, London, Tokyo, Istanbul, and Jakarta), and contains a total of 2,293,716 check-ins from 24,068 individuals in 397,610 venues over a period of 140 days.…”

“…They are either public or collected with consent as follows: The Foursquare data were derived from open public posts on Twitter between 2012 and 2014 by researchers at University of Freibiurg and made available online ( https://sites.google.com/site/yangdingqi/home/foursquare-dataset ). Details of the data has been published previously 25 , 26 . The University and Bike datasets were collected from adult participants with informed consent.…”

“…The Foursquare data were derived from open public posts on Twitter between 2012 and 2014 by researchers at University of Freibiurg and made available online ( https://sites.google.com/site/yangdingqi/home/foursquare-dataset ). Details of the data has been published previously 25 , 26 .…”

Trajectory similarity measurement: An enhanced maximal travel match method

“…In this space, each trajectory is represented by a vector that may constitute a more meaningful representation for machine learning methods, such as neural networks (Petry, Leite Da Silva, Esuli, Renso, & Bogorny, 2020), to identify similar trajectories. We refer the reader to Gao et al (2017, 2020), Yang, Qu, Yang, and Cudre‐Mauroux (2020), and Zhou, Zhao, Zhang, Wen, and Wang (2016) for further information.…”

Deep Learning-Based Community Detection Approach on Multimedia Social Networks

“…Graph [11] Multimedia objects, concepts Multimedia annotation [12] Images, users, and tags Link-based similarity Bipartite [13] Users and contents Influence diffusion [14] Users and contents Social recommendation Tripartite [15] Users, tags, and images Recommendation [16] Users, interaction behavior, and tags Recommendation [17] Users, Tweets, and topics Coronavirus analysis Hypergraph [18] Users, tags, and resources Consensus maximization [19] Users, time, and POIs Location prediction [20] Users and items Recommendation…”