Parham Moradi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Parham Moradi has a total of 90 co-authors. Here are the top co-authors by number of shared publications:
- Mahdi Jalili
RMIT University
9 shared publications Mahdi Jalili
4 shared publicationsAbdulrahman Lotfi
3 shared publications- Amir Sheikhahmadi
RMIT University
3 shared publications - Masoud Karimzadeh
Department of Computer Engineering, Sa. C., Islamic Azad University, Sanandaj, Iran
3 shared publications - Siamak Ghodsi
Department of computer engineering, University of Kurdistan, Sanandaj, Iran
3 shared publications
Latest Publications
- Open Access
- 29 June 2026
- Published by Elsevier in Information Sciences
- Vol. 756
A multi-teacher knowledge distillation framework with hypergraph neural networks and language models for mitigating sparsity in recommender systems
- 29 June 2026
- Published by Elsevier in Information Sciences
- Vol. 756
Open AccessA multi-teacher knowledge distillation framework with hypergraph neural networks and language models for mitigating sparsity in recommender systems
- Open Access
- 5 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
An explainable multi-modal recommender system integrating graph neural networks and language models
- 5 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
Open AccessAn explainable multi-modal recommender system integrating graph neural networks and language models
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1183-1194
AC$ 2 $L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1183-1194
Open AccessAC$ 2 $L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection
- Open Access
- 18 October 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 162
A graph-based knowledge distillation framework for drug repurposing via multi-task learning
- 18 October 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 162
Open AccessA graph-based knowledge distillation framework for drug repurposing via multi-task learning
- 17 September 2025
- Published by Springer Nature in Iranian Journal of Science
- Vol. 50  (2) , 683-700
Graph regularized weighted symmetric nonnegative matrix factorization for data clustering
- 17 September 2025
- Published by Springer Nature in Iranian Journal of Science
- Vol. 50  (2) , 683-700
Graph regularized weighted symmetric nonnegative matrix factorization for data clustering
- 2 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81  (14) , 1-29
Robust dual space factorization for unsupervised feature selection (RDSF-UFS)
- 2 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81  (14) , 1-29
Robust dual space factorization for unsupervised feature selection (RDSF-UFS)
- Open Access
- 1 September 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 161
Maximum relevant minimum redundant multi-label feature selection using ant colony optimization
- 1 September 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 161
Open AccessMaximum relevant minimum redundant multi-label feature selection using ant colony optimization
- Open Access
- 6 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Multi-structural view knowledge distillation for node influence prediction in complex networks
- 6 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Open AccessMulti-structural view knowledge distillation for node influence prediction in complex networks
- Open Access
- 15 May 2025
- Published by Springer Nature in Research Square
Robust Dual Space Factorization for Unsupervised Feature Selection (RDSF-UFS)
Unsupervised feature selection is critical in high-dimensional data analysis, as it identifies the most informative features without relying on label information. In this paper, we propose a novel Robust Dual Space Factorization for Unsupervised Feature Selection (RDSF-UFS) framework based on Symmetric Nonnegative Matrix Factorization (SNMF) and Nonnegative Matrix Tri-Factorization (NMTF). The proposed method explores sample and feature affinity matrices to capture intrinsic data structures in a dual latent space. Specifically, we introduce a robust objective function incorporating the Frobenius and à µÃ°¿ 2,1 norms to enhance resistance to noise and outliers. We further impose an orthogonality constraint on the latent factor matrices to promote sparsity and improve clustering performance. An efficient optimization algorithm is derived to iteratively update the latent factors by solving the associated gradient-based equations. We evaluated the performance of RDSFUFS on eight benchmark datasets, including biological microarray, face image, speech signal, and digit image datasets. Experimental results demonstrate that RDSFUFS outperforms state-of-the-art feature selection methods in terms of Normalized Mutual Information (NMI) and Accuracy (ACC), highlighting its ability to uncover meaningful feature patterns and improve clustering performance.
- 15 May 2025
- Published by Springer Nature in Research Square
Open AccessRobust Dual Space Factorization for Unsupervised Feature Selection (RDSF-UFS)
Unsupervised feature selection is critical in high-dimensional data analysis, as it identifies the most informative features without relying on label information. In this paper, we propose a novel Robust Dual Space Factorization for Unsupervised Feature Selection (RDSF-UFS) framework based on Symmetric Nonnegative Matrix Factorization (SNMF) and Nonnegative Matrix Tri-Factorization (NMTF). The proposed method explores sample and feature affinity matrices to capture intrinsic data structures in a dual latent space. Specifically, we introduce a robust objective function incorporating the Frobenius and à µÃ°¿ 2,1 norms to enhance resistance to noise and outliers. We further impose an orthogonality constraint on the latent factor matrices to promote sparsity and improve clustering performance. An efficient optimization algorithm is derived to iteratively update the latent factors by solving the associated gradient-based equations. We evaluated the performance of RDSFUFS on eight benchmark datasets, including biological microarray, face image, speech signal, and digit image datasets. Experimental results demonstrate that RDSFUFS outperforms state-of-the-art feature selection methods in terms of Normalized Mutual Information (NMI) and Accuracy (ACC), highlighting its ability to uncover meaningful feature patterns and improve clustering performance.
- Open Access
- 10 February 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 273
Two-level attention mechanism with contrastive learning for heterogeneous graph representation learning
- 10 February 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 273
Open AccessTwo-level attention mechanism with contrastive learning for heterogeneous graph representation learning