A survey on graph counterfactual explanations: definitions, methods, evaluation, and research challenges

MA Prado-Romero, B Prenkaj, G Stilo… - ACM Computing …, 2024 - dl.acm.org
Graph Neural Networks (GNNs) perform well in community detection and molecule
classification. Counterfactual Explanations (CE) provide counter-examples to overcome the …

[HTML][HTML] A novel nonnegative matrix factorization-based model for attributed graph clustering by incorporating complementary information

V Jannesari, M Keshvari, K Berahmand - Expert Systems with Applications, 2024 - Elsevier
Attributed graph clustering is a prominent research area, catering to the increasing need for
understanding real-world systems by uncovering exhaustive meaningful latent knowledge …

A review on community detection in large complex networks from conventional to deep learning methods: A call for the use of parallel meta-heuristic algorithms

MN Al-Andoli, SC Tan, WP Cheah, SY Tan - IEEE Access, 2021 - ieeexplore.ieee.org
Complex networks (CNs) have gained much attention in recent years due to their
importance and popularity. The rapid growth in the size of CNs leads to more difficulties in …

Graph regularized nonnegative matrix factorization for community detection in attributed networks

K Berahmand, M Mohammadi… - … on Network Science …, 2022 - ieeexplore.ieee.org
Community detection has become an important research topic in machine learning due to
the proliferation of network data. However, most existing methods have been developed …

Self-supervised temporal graph learning with temporal and structural intensity alignment

M Liu, K Liang, Y Zhao, W Tu, S Zhou… - … on Neural Networks …, 2024 - ieeexplore.ieee.org
Temporal graph learning aims to generate high-quality representations for graph-based
tasks with dynamic information, which has recently garnered increasing attention. In contrast …

WSNMF: Weighted symmetric nonnegative matrix factorization for attributed graph clustering

K Berahmand, M Mohammadi, R Sheikhpour, Y Li… - Neurocomputing, 2024 - Elsevier
Abstract In recent times, Symmetric Nonnegative Matrix Factorization (SNMF), a derivative of
Nonnegative Matrix Factorization (NMF), has surfaced as a promising technique for graph …

Obfuscating community structure in complex network with evolutionary divide-and-conquer strategy

J Zhao, KH Cheong - IEEE Transactions on Evolutionary …, 2023 - ieeexplore.ieee.org
As the number of social network users grows exponentially with increasingly complex
profiles, community detection algorithms play a critical role in user portrait analysis. The …

DAC-HPP: deep attributed clustering with high-order proximity preserve

K Berahmand, Y Li, Y Xu - Neural Computing and Applications, 2023 - Springer
Attributed graph clustering, the task of grou** nodes into communities using both graph
structure and node attributes, is a fundamental problem in graph analysis. Recent …

A learning convolutional neural network approach for network robustness prediction

Y Lou, R Wu, J Li, L Wang, X Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Network robustness is critical for various societal and industrial networks against malicious
attacks. In particular, connectivity robustness and controllability robustness reflect how well a …

A self-adaptive evolutionary deception framework for community structure

J Zhao, Z Wang, J Cao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The rapid development of community detection algorithms, while serving users in social
networks, also brings about certain privacy problems. In this work, we study community …