Attributed Graph Embedding with Random Walk Regularization and Centrality-Based Attention

Article Computer Science, Artificial Intelligence

Deep neighbor-aware embedding for node clustering in attributed graphs

Chun Wang et al.

Summary: Node clustering is a method to partition the vertices in a graph into multiple groups or communities. Existing studies mainly focus on developing deep learning approaches to learn a latent representation of nodes, followed by simple clustering methods like k-means. In this paper, a clustering-directed deep learning approach called DNENC is proposed to encode the topological structure and node content in a graph, and generate soft labels for a self-training process to iteratively refine the node clustering results.

PATTERN RECOGNITION (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Graph embedding clustering: Graph attention auto-encoder with cluster-specificity distribution

Huiling Xu et al.

Summary: In recent years, many graph embedding clustering methods have been developed, but most of them do not consider the cluster-specificity distribution of node representations, leading to suboptimal clustering performance. This study proposes a new deep graph attention auto-encoder for node clustering, which combines self-attention mechanism and node attribute reconstruction to improve node representation learning with a cluster-specificity distribution constraint.

NEURAL NETWORKS (2021)

Add to Collection

Article Multidisciplinary Sciences

Mobility network models of COVID-19 explain inequities and inform reopening

Serina Chang et al.

Summary: The study introduces a SEIR model that integrates fine-grained, dynamic mobility networks to simulate the spread of COVID-19 in the ten largest US metropolitan areas. By accurately fitting the real case trajectory, the model identifies the effectiveness of restricting maximum occupancy at locations for curbing infections and reveals the contributions of mobility-related mechanisms to higher infection rates among disadvantaged socioeconomic and racial groups.

NATURE (2021)

Add to Collection

Article Engineering, Electrical & Electronic