Latest Articles for Social Networks

Introducing Directional Graph Attention Network for improved node learning in complex graphs.

A novel approach to graph domain adaptation without needing labeled data.

A new model improves link prediction in multiplex social networks.

Learn how triangles in networks reveal connections and enhance analysis.

This article examines how differences impact group opinion formation.

A fresh look at grouping points in graphs for balanced clusters.

This study explores how topology awareness affects Graph Neural Network performance and fairness.

Discover how relationships evolve over time with temporal networks.

This study focuses on memory effects for better community detection in changing networks.

A multi-objective method for maximizing influence while considering various factors.

This study examines how networks grow using clustering attachment methods.

Explore how coloring impacts mathematics and its real-world applications.

Exploring role assignments in graphs and their applications in various fields.

A look into the complexities of identifying densest subgraphs in various graph structures.

A fresh approach to estimating causal effects in social networks.

Examining methods to alter graphs into equal-sized cliques.

A new method improves link prediction by addressing noisy and incomplete data.

A new method identifies unusual patterns in evolving networks to enhance anomaly detection.

A look at how to maintain strong connectivity in directed graphs through partitioning.

A framework enhances next-point-of-interest recommendations using large language models and contextual data.

A look into how fire spreads across networks and its significance in social dynamics.

GLAD enhances graph generation through a discrete latent space and diffusion bridges.

Study reveals methods for inferring data despite malicious corruption challenges.

Examining how connections shape social dynamics in networks.

Exploring how attractive and repulsive connections shape cluster synchronization in networks.

A new approach to understanding graph structures from node signals.

Innovative methods in counting subgraphs using graph kernels for various applications.

Exploring random walks to analyze complex data structures effectively.

A look at how complex systems influence behaviors and interactions.

Explore the fundamentals and applications of graph theory in various fields.

A strategy to protect sensitive connections in graph data while releasing useful information.

A new method improves accuracy in studying network influences.

New methods for graph clustering allow for flexible grouping without knowing cluster numbers.

A new approach to understanding evolving networks through autoregressive modeling.

CoNHD enhances hypergraph modeling for complex relationships with edge-dependent classification.

A new method improves network predictions by examining node relationships through orbit adjacency.

Exploring the link between soft happy colouring and community detection in networks.

TAGA offers a new way to analyze Text-Attributed Graphs without extensive labeled data.

A look into methods and challenges in predicting connections in dynamic networks.

Discover how random hyperbolic graphs represent real-world networks effectively.