Mostafa H. Chehreghani

Mostafa H. Chehreghani

Assistant Professor
Amirkabir University of Technology (Tehran Polytechnic)
📧 mostafa.chehreghani@gmail.com 📧 mostafa.chehreghani@aut.ac.ir 🎓 Google Scholar

Short Bio

Mostafa H. Chehreghani received his Master's degree in Computer Engineering (Software) in 2007 from the University of Tehran, Iran. From 2007 to 2010, he worked as a programmer in Iran. He then pursued his PhD studies with the Machine Learning Group at KU Leuven. After completing his doctorate, he joined Institut Polytechnique de Paris as a researcher. Since February 2019, he has been an assistant professor at Amirkabir University of Technology (Tehran Polytechnic).

Research Interests

  • Graph-based machine learning
  • Graph algorithms
  • Philosophy of artificial intelligence
  • Machine learning, data analytics and AI

Professional Activities

Publications

2026

  1. Disentangling popularity and quality: An edge classification approach for fair recommendation
    Nemat Gholinejad, Mostafa Haghir Chehreghani. Applied Soft Computing, 201, 115619. doi:10.1016/j.asoc.2026.115619
  2. PBiLoss: Popularity-aware regularization to improve fairness in graph-based recommender systems
    Mohammad Naeimi, Mostafa Haghir Chehreghani. Applied Soft Computing, 200, 115449. doi:10.1016/j.asoc.2026.115449
  3. Singular value decomposition-based graph densification for link prediction in sparse graphs
    Amir Hossein Pouria, Mostafa Haghir Chehreghani, Alireza Bagheri. The Computer Journal, bxaf144.
  4. Diffusion-aware graph refinement for graph-level classification and property detection
    Seyedeh Fatemeh Mousavi, Mohammad Rahmati, Mostafa Haghir Chehreghani. Engineering Applications of Artificial Intelligence, 163, 113157.
  5. Quantifying Iran's endemic transition in COVID-19 through Omicron reproduction number estimates
    Dorsa Macky Aleagha, Payam Zohari, Mostafa Haghir Chehreghani. Physica A: Statistical Mechanics and its Applications, 688, 131422.
  6. Heterophily-aware fair recommendation using graph convolutional networks
    Nemat Gholinejad, Mostafa Haghir Chehreghani. Neurocomputing, 661, 131956.

2025

  1. A Decision-Based Heterogenous Graph Attention Network for Multi-Class Fake News Detection
    Batool Lakzaei, Mostafa Haghir Chehreghani, Alireza Bagheri. Knowledge-Based Systems, 330, 114499.
  2. Mitigating Over-Squashing in Graph Few-Shot Learning by Leveraging Local and Global Similarities
    Yassin Mohamadi, Mostafa Haghir Chehreghani. Applied Soft Computing, 184, 113863.
  3. Mitigating Over-Smoothing in Graph Neural Networks for Node Classification through Adaptive Early Embedding and Biased DropEdge Procedures
    Fateme Hoseynnia, Mehdi Ghatee, Mostafa Haghir Chehreghani. Knowledge-Based Systems, 320, 113615.
  4. LOSS-GAT: Label Propagation and One-Class Semi-Supervised Graph Attention Network for Fake News Detection
    Batool Lakzaei, Mostafa Haghir Chehreghani, Alireza Bagheri. Applied Soft Computing, 174, 112965.
  5. Content-augmented graph neural networks
    Fatemeh Gholamzadeh, Pegah Zahedi, Amirhossein Kashani, Mostafa Haghir Chehreghani. ACM Transactions on the Web, 19(4), pp. 1-19.
  6. Prosody Recognition in Persian Poetry
    Mohammadreza Shahrestani, Mostafa Haghir Chehreghani. Speech Communication, 170, 103222.
  7. Mining transactional tree databases under homeomorphism
    Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani. The Journal of Supercomputing, 81(4), 530.

2024

  1. A review on the impact of data representation on model explainability
    Mostafa Haghir Chehreghani. ACM Computing Surveys, 56(10).
  2. Centrality-based and similarity-based neighborhood extension in graph neural networks
    Mohammad Javad Zohrabi, Saeed Saravani, Mostafa Haghir Chehreghani. The Journal of Supercomputing, 80(16): 24638-24663.
  3. Hierarchical correlation clustering and tree preserving embedding
    Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani. CVPR 2024, pp. 23083-23093.
  4. The embeddings world and Artificial General Intelligence
    Mostafa Haghir Chehreghani. Cognitive Systems Research, 84, 101201.
  5. Disinformation detection using graph neural networks: a survey
    Batool Lakzaei, Mostafa Haghir Chehreghani, Alireza Bagheri. Artificial Intelligence Review, 57(3): 52.

2023

  1. Non-uniform sampling methods for large itemset mining
    Zahra Moteshaker Arani, Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani. IEEE Big Data 2023, pp. 5714-5722.
  2. A deep comprehensive model for stock price prediction
    Mehdi Salemi Mottaghi, Mostafa Haghir Chehreghani. Journal of Ambient Intelligence and Humanized Computing, 14(8), pp. 11385-11395.
  3. Improving empirical efficiency of CUR decomposition
    Mostafa Haghir Chehreghani, Zahra Yaghoubi. The Journal of Supercomputing, 79(8), pp. 9350-9366.
  4. On using affine sketches for multiple-response dynamic graph regression
    Mostafa Haghir Chehreghani. The Journal of Supercomputing, 79(5), pp. 5139-5153.

2022

  1. On using node indices and their correlations for fake account detection
    Sara Asghari, Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani. IEEE BigData 2022, pp. 5646-5651.
  2. Graph clustering using node embeddings: an empirical study
    Mahdi Ghanbari, Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani. IEEE BigData 2022, pp. 5478-5483.
  3. On the theory of dynamic graph regression problem
    Mostafa Haghir Chehreghani. Computational and Applied Mathematics, 41(8).
  4. Half a decade of graph convolutional networks
    Mostafa Haghir Chehreghani. Nature Machine Intelligence, 4(3), pp. 192-193.
  5. Non-uniform PageRank using node features and node embeddings
    Fatemeh Keshvari, Mostafa Haghir Chehreghani. JCSIT (in Persian).

2021

  1. Shallow Node Representation Learning using Centrality Indices
    Masoud Malek, Mostafa Haghir Chehreghani, Ehsan Nazerfard, Morteza Haghir Chehreghani. IEEE BigData 2021, pp. 5209-5214.
  2. Sublinear update time randomized algorithms for dynamic graph regression
    Mostafa Haghir Chehreghani. Applied Mathematics and Computation, 410, 126434.
  3. Dynamical algorithms for data mining and machine learning over dynamic graphs
    Mostafa Haghir Chehreghani. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 11(2).
  4. Exact and Approximate Algorithms for Computing Betweenness Centrality in Directed Graphs
    Mostafa Haghir Chehreghani, Albert Bifet, Talel Abdessalem. Fundamenta Informaticae, 182(3), pp. 219-242.

2020

  1. Subsampled Randomized Hadamard Transform for Regression of Dynamic Graphs
    Mostafa Haghir Chehreghani. CIKM 2020, pp. 2045-2048.
  2. Learning representations from dendrograms
    Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani. Machine Learning, 109(9-10), pp. 1779-1802.
  3. Sampling informative patterns from large single networks
    Mostafa Haghir Chehreghani, Talel Abdessalem, Albert Bifet, Meriem Bouzbila. Future Generation Computer Systems, 106, pp. 653-658.

2019

  1. Adaptive Algorithms for Estimating Betweenness and k-path Centralities
    Mostafa Haghir Chehreghani, Albert Bifet, Talel Abdessalem. CIKM 2019, pp. 1231-1240.
  2. Metropolis-Hastings algorithms for estimating betweenness centrality
    Mostafa Haghir Chehreghani, Talel Abdessalem, Albert Bifet. EDBT 2019, pp. 686-689.

2018

  1. DyBED: an efficient algorithm for updating betweenness centrality in directed dynamic graphs
    Mostafa Haghir Chehreghani, Albert Bifet, Talel Abdessalem. IEEE BigData 2018, pp. 2114-2123.
  2. An in-depth comparison of group betweenness centrality estimation algorithms
    Mostafa Haghir Chehreghani, Albert Bifet, Talel Abdessalem. IEEE BigData 2018, pp. 2104-2113.
  3. Discriminative distance-based network indices with application to link prediction
    Mostafa Haghir Chehreghani, Albert Bifet, Talel Abdessalem. The Computer Journal, 61(7), pp. 998-1014.
  4. Efficient context-aware k-nearest neighbor search
    Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani. ECIR 2018, pp. 466-478.
  5. Efficient exact and approximate algorithms for computing betweenness centrality in directed graphs
    Mostafa Haghir Chehreghani, Albert Bifet, Talel Abdessalem. PAKDD 2018, pp. 752-764.

2017

  1. Upper and lower bounds for the q-entropy of network models with applications to network model selection
    Mostafa Haghir Chehreghani, Talel Abdessalem. Information Processing Letters, 119, pp. 1-8.

2016

  1. A framework for description and analysis of sampling-based approximate triangle counting algorithms
    Mostafa Haghir Chehreghani. DSAA 2016.
  2. Modeling transitivity in complex networks
    Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani. UAI 2016.
  3. Transactional tree mining
    Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani. ECML-PKDD 2016.
  4. Mining rooted ordered trees under subtree homeomorphism
    Mostafa Haghir Chehreghani, Maurice Bruynooghe. Data Mining and Knowledge Discovery, 30(5), pp. 1249-1272.

2014

  1. An efficient algorithm for approximate betweenness centrality computation
    Mostafa Haghir Chehreghani. The Computer Journal, 57(9), 1371-1382.
  2. Effective co-betweenness centrality computation
    Mostafa Haghir Chehreghani. WSDM 2014.
  3. Graph and Network Pattern Mining
    Jan Ramon, Constantin Comendant, Mostafa Haghir Chehreghani, Yuyi Wang. Mining User Generated Content 2014, pp. 97-126.

2013

  1. An efficient algorithm for approximate betweenness centrality computation
    Mostafa Haghir Chehreghani. CIKM 2013.
  2. Mining large networks under homomorphism
    Mostafa Haghir Chehreghani, Jan Ramon, Thomas Fannes. Dutch-Belgian Database Day (DBDBD), Rotterdam, The Netherlands, 29 November 2013.

2012

  1. Probabilistic heuristics for hierarchical web data clustering
    Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani, Hassan Abolhassani. Computational Intelligence, 28(2), pp. 209-233.

2011

  1. Efficiently mining unordered trees
    Mostafa Haghir Chehreghani. ICDM 2011 (winner of IEEE student travel grant award).
  2. OInduced: an efficient algorithm for mining induced patterns from rooted ordered trees
    Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani, Caro Lucas, Masoud Rahgozar. IEEE Transactions on Systems, Man, and Cybernetics - Part A, 41(5), pp. 1013-1025.

2010

  1. On the complexity of listing closed frequent subgraph patterns
    Jan Ramon, Mostafa Haghir Chehreghani. French Conference on Combinatorics (8FCC).

2009

  1. Efficient rule based structural algorithms for classification of tree structured data
    Mostafa Haghir Chehreghani, Morteza Haghir Chehreghani, Caro Lucas, Masoud Rahgozar, Euhanna Ghadimi. Intelligent Data Analysis, 13(1).
  2. Density link-based methods for clustering web pages
    Morteza Haghir Chehreghani, Hassan Abolhassani, Mostafa Haghir Chehreghani. Decision Support Systems, 47(4), pp. 374-382.

2008

  1. Improving density-based methods for hierarchical clustering of the web pages
    Morteza Haghir Chehreghani, Hassan Abolhassani, Mostafa Haghir Chehreghani. Data and Knowledge Engineering, 67(1), pp. 30-50.

2007

  1. Attaining higher quality for density based data mining algorithms
    Morteza Haghir Chehreghani, Hassan Abolhassani, Mostafa Haghir Chehreghani. RR 2007, LNCS 4524, pp. 329-338.
  2. Modeling an agent-based system using Rebeca
    Reza Basseda, Mostafa Haghir Chehreghani, Fattaneh Taghiyareh. FSEN 2007.

Teaching

  • Algorithms of Big Data Analytics (Amirkabir University of Technology, 2020–now)
  • Complex Networks Analysis (Amirkabir University of Technology, 2019–now)
  • Linear Algebra (Amirkabir University of Technology, 2019–now)
  • Discrete Mathematics (Amirkabir University of Technology, 2019–2025)
  • Web Data (Institut Polytechnique de Paris, 2017–2018)
  • Big Data Mining (Institut Polytechnique de Paris, 2017–2018)
  • Machine Learning and Data Mining (Institut Polytechnique de Paris, 2017)

PhD Students

  • Mohammad Amin Javaheri (co-supervisor) – topic: improving unsupervised robustness in graph neural networks
  • Rozhin Naseri (supervisor)
  • MohammadHossein Hooshmand (co-supervisor)
  • Seyedeh Fatemeh Mousavi (advisor)
  • (Graduated) Fatemeh HosseinNia (advisor) – topic: node classification in graph neural networks using adaptive learning
  • (Graduated) Batool Lakzaei (co-supervisor) – topic: fake news detection in online social networks

Master Students

  • Mohammadreza Safran – topic:
  • Amir Rajabi – topic:
  • Ayeh Zoghi – topic:
  • Milad Fathi – topic:
  • Poya Rezvani – topic:
  • Payam Zohari – topic:
  • Dorsa Macky Aleagha – topic:
  • Helia Ghorbani-Asl – topic: improving code generation using large language models and graph neural networks
  • Amin Motavasseli – topic: code comment generation using generative AI
  • Mohammad Pourbakht – topic: improving cancer diagnosis using graph neural networks
  • (Graduated) Zahra Akhlaghi – topic: improving dynamic recommender systems
  • (Graduated) Mohammad Naeimi – topic: improving music recommender systems using hybrid methods
  • (Graduated) Narges Nemati Shamsabad – topic: matrix completion with application to recommender systems
  • (Graduated) AmirHossein Kashani – topic: scalable routing and passenger matching algorithm for shared taxi services
  • (Graduated) Yasin Mohamadi – topic: improving zero/few shot learning over graphs
  • (Graduated) Nemat Gholinejad – topic: developing a graph-based multi-stockholder recommendation system
  • (Graduated) Mohammad Moradi – topic: user credibility estimation in online social networks
  • (Graduated) Fateme Gholamzade Nasrabadi – topic: embedding computation for heterogeneous data
  • (Graduated) Moein Salimi – topic: developing a scalable distributed framework for learning graph representations
  • (Graduated) Mohammad Javad Zohrabi – topic: improving abstractive text summarization
  • (Graduated) Masoud Malek – topic: link prediction in complex networks
  • (Graduated) Seyed Mohammad Mirabdolbaghi – topic: sentiment analysis in persian social networks
  • (Graduated) Mehdi Salemi Mottaghi – topic: Iran stock market prediction using machine learning
  • (Graduated) Meriem Bouzbila (Institut Polytechnique de Paris) – topic: sampling informative patterns from large networks