.png){kind=icon}
.png){kind=icon}
Return
Bayes-Enhanced Multi-View Attention Networks for Robust POI Recommendation
.png){kind=icon}
OA
AI
J
Y
S
H
J
P
DOI：10.1109/TKDE.2023.3329673.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
POI recommendation can facilitate various Location-Based Social Network services. Existing methods generally assume the available POI check-ins are the ground-truth depiction of user behaviors. However, in real scenarios, check-in data can be rather unreliable due to both subjective and objective causes including positioning errors and user privacy concerns. The data uncertainty issue may lead to significant negative impacts on POI recommendation, but has not been fully explored. To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of user check-ins, and propose a Bayes-enhanced Multi-view Attention Network to effectively address it. Specifically, we construct three POI graphs to comprehensively model the dependencies among the POIs from different views, including the personal POI transition graph, the semantic-based and distance-based POI graphs. As the personal graph is usually sparse and sensitive to noise, we design a Bayes-enhanced spatial dependency learning module for data augmentation from the local view. A Bayesian posterior guided graph augmentation approach is adopted to generate a new graph with collaborative signals to increase the data diversity and thus counteract the data uncertainty issue. Next, a multi-view attention-based user preference learning module is proposed. By incorporating the semantic and distance correlations of POIs, the user preference can be effectively refined and finally achieve robust recommendations. We conduct extensive experiments over three datasets. The results show that our proposal significantly outperforms the state-of-the-art methods in POI recommendation when the available check-ins are incomplete and noisy.
Keywords:
Correlation
Semantics
Noise measurement
Collaboration
Uncertainty
Bayes methods
Representation learning
POI recommendation
Bayesian neural network
robust machine learning
Journal
IF:
10.4
Papers:
6.7K
Citations:
3.2W
Organization
Cited Papers