Explainable Artificial Intelligence for Social Network Analysis: A Graph-based Framework

Even-if Explanations for Graph Neural Networks

A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit

Counterfactual explanations for graph-structured data seek to determine minimal and realistic modifications required in an input graph to alter a model's prediction to a predefined output. Although counterfactual explainers that support modifying the graph by both adding and removing edges have recently emerged, there...

Explainable Recommendation in Graph Neural Networks Using Propagation Path Analysis and Counterfactual Graph Editing

A post-hoc explainability framework for LightGCN is proposed combining two complementary techniques: Propagation Path Analysis, which decomposes recommendation scores by propagation layer to attribute influence to specific training interactions, and Counterfactual Graph Editing, which identifies the most influential us...

Graph Analytics for Social Networks

This paper conducts a case study on Zachary's Karate Club network and a synthetically generated scale-free network, computing centrality measures, detecting communities using the Louvain algorithm, and analysing degree-distribution behavior.

Soft Trioid Graphs for Dynamic Social Network Analysis

Soft trioid graphs integrate parameterized algebra with graph theory to model systems exhibiting both algebraic structure and relational connectivity under varying contexts. This paper applies the framework to dynamic social network analysis, demonstrating that semilattice decomposition of an idempotent network yields...

Evaluation of student social networks using graph neural networks (GNN)

A Multi-Channel Decoupled Attention Graph Neural Network (MCDA-GNN) is proposed for the comprehensive evaluation of student social networks, providing a scientific basis for personalized educational interventions, campus community optimization, and mental health early warning.