Yong Wang’s research while affiliated with China University of Geosciences and other places

Friend link prediction is an important issue in recommendation systems and social network analysis. In Location-Based Social Networks (LBSNs), predicting potential friend relationships faces significant challenges due to the diversity of user behaviors, along with the high dimensionality, sparsity, and complex noise in the data. To address these issues, this paper proposes a Heterogeneous Graph Attention Network (GEVEHGAN) model based on Lite Gate Recurrent Unit (Lite-GRU) embedding and Variational Autoencoder (VAE) enhancement. The model constructs a heterogeneous graph with two types of nodes and three types of edges; combines Skip-Gram and Lite-GRU to learn Point of Interest (POI) and user node embeddings; introduces VAE for dimensionality reduction and denoising of the embeddings; and employs edge-level attention mechanisms to enhance information propagation and feature aggregation. Experiments are conducted on the publicly available Foursquare dataset. The results show that the GEVEHGAN model outperforms other comparative models in evaluation metrics such as AUC, AP, and Top@K accuracy, demonstrating its superior performance in the friend link prediction task.

With the rapid growth of location-based social network (LBSN), rich data comprising social behaviors and location information among users has emerged. Predicting potential friendships accurately from abundant information has become a pivotal research area. While graph neural network (GNN) have shown significant promise in prediction, existing approaches often fail to fully exploit the heterogeneous data characteristics in LBSN. Key challenges include inadequate modeling of the intricate relationships between users and points of interest (POI), overlooking the significance of spatial-temporal information in user trajectories, and underutilizing rich edge features. To address these challenges, we design a novel GRU-enhanced Heterogeneous Multigraph Attention Network (GEHMAN), which is a GNN model enhanced by GRU. We construct a heterogeneous multigraph to comprehensively capture user-POI relationships. We then employ a skip-gram model to embed POI nodes from user sub-trajectories and use RNN with GRU units to embed user nodes. GEHMAN utilize hierarchical attention mechanism to consolidate node information by aggregating diverse types of neighboring nodes and connecting edges. Experiments on six real city datasets show that compared with the best performance of six benchmark methods including LBSN2vec++, Metapath2vec and HAN, the average improvement percentages of GEHMAN in AUC, AP, and Top@K are 2.225%, 1.948%, and 6.353%, respectively.

Remote sensing image semantic segmentation plays a crucial role in various fields, such as environmental monitoring, urban planning, and agricultural land classification. However, most current research primarily focuses on utilizing the spatial and spectral information of single-temporal remote sensing images, neglecting the valuable temporal information present in historical image sequences. In fact, historical images often contain valuable phenological variations in land features, which exhibit diverse patterns and can significantly benefit from semantic segmentation tasks. This paper introduces a semantic segmentation framework for satellite image time series (SITS) based on dilated convolution and a Transformer encoder. The framework includes spatial encoding and temporal encoding. Spatial encoding, utilizing dilated convolutions exclusively, mitigates the loss of spatial accuracy and the need for up-sampling, while allowing for the extraction of rich multi-scale features through a combination of different dilation rates and dense connections. Temporal encoding leverages a Transformer encoder to extract temporal features for each pixel in the image. To better capture the annual periodic patterns of phenological phenomena in land features, position encoding is calculated based on the image’s acquisition date within the year. To assess the performance of this framework, comparative and ablation experiments were conducted using the PASTIS dataset. The experiments indicate that this framework achieves highly competitive performance with relatively low optimization parameters, resulting in an improvement of 8 percentage points in the mean Intersection over Union (mIoU).