|
Morteza Haghir Chehreghani
Associate Professor Data Science and AI Division Department of Computer
Science and Engineering Chalmers University of Technology |
|
Home Since 2018, I am an Associate Professor in Machine Learning and Artificial Intelligence at the
Department of Computer
Science and Engineering, Chalmers
University of Technology. I received my Ph.D. from ETH Zurich (Switzerland) in Computer Science in 2014, where I worked at
the Institute for Machine Learning
under the supervision of Prof. Joachim M.
Buhmann. After the Ph.D., I spent about four years at Xerox Research
Centre Europe (later called Naver
Labs Europe) as a researcher (Staff Research Scientist I, and then Staff
Research Scientist II). Research Artificial Intelligence,
Machine Learning and Data Science constitute my general research interests. In particular, I am interested in Under-Supervised Machine
Learning and Decision Making, i.e., the AI-based decision-making problems that need to deal with the lack of sufficient available information (e.g., labelled data,
decision parameters, uncertainty and beyond). I study these problems in the contexts of Interactive Machine Learning and Unsupervised Learning: § Interactive Machine Learning [current research] o
Active learning and active decision making o Online learning
(Bandits) o
(Deep) Reinforcement learning o
Human-in-the-loop machine learning o
Generative AI and large language models (LLMs) in interaction o Deep learning for interactive learning §
Unsupervised
Learning [more in the past] o
Cluster
modelling o
Unsupervised
representation learning o
Learning
theory and generalization performance of unsupervised learning My research has
been applied to several real-world problems in domains such as
transport, life science, energy, autonomous systems, recommendation, and decision support systems. Teaching o
Advanced Topics in Machine Learning (reinforcement
learning, online learning, active learning, and relevant deep learning
models), Spring 2023. o
Algorithms for Machine Learning and
Inference, Spring 2023. o
Advanced Topics in Machine Learning (reinforcement
learning, online learning, active learning, and relevant deep learning
models), Spring 2022. o
Algorithms for Machine Learning and
Inference, Spring 2022. o
Advanced Topics in Machine Learning
(reinforcement learning, online learning, active learning, and relevant deep
learning models), Spring 2021. o Algorithms for Machine Learning and Inference,
Spring 2021. o Algorithms for Machine Learning and Inference,
Spring 2020. o Statistical Methods
for Data Science, with Magnus V. Persson, Fall 2019. o Theoretical
Foundations of Machine Learning (PhD course), with Devdatt Dubhashi, Fredrik
Johansson, Ashkan Panahi, Fall 2019. o An intense course
on Machine Learning to the Chalmers CSE faculty, June 2019. o Algorithms for Machine Learning and Inference,
Spring 2019. o Statistical Methods
for Data Science, with Richard Johansson, Fall 2018. o Algorithms for Machine Learning and Inference,
with Devdatt Dubhashi, Spring 2018. o ML-HW CoDesign
(Efficient Deep Learning, PhD course), with Fredrik Dahlgren, Devdatt
Dubhashi, Olof Mogren, Miquel Pericas, Pedro Petersen, Ioannis Sourdis and
Per Stenström, Spring 2018. Contact
Department of Computer Science and Engineering SE-412 96 Göteborg Sweden https://www.chalmers.se/en/persons/haghir/
Publications
* Pre-prints can be found in the arXiv and DBLP profiles.ss [1] Arman Rahbar, Ashkan Panahi, Morteza
Haghir Chehreghani, Devdatt Dubhashi, and Hamid Krim, “Recovery Bounds on Class-Based
Optimal Transport: A Sum-of-Norms Regularization Framework”, 40th
International Conference on Machine Learning (ICML), 2023. [2] Arman Rahbar, Ziyu Ye, Yuxin Chen, and Morteza Haghir Chehreghani, “Efficient Online Decision
Tree Learning with Active Feature Acquisitions”, 32nd International
Joint Conference on Artificial Intelligence (IJCAI), 2023. [3] Niklas
Åkerblom, Yuxin Chen, and Morteza Haghir
Chehreghani,
“Online
Learning of Energy Consumption for Navigation of Electric Vehicles”, Artificial
Intelligence, 317, 2023. [4] Morteza Haghir Chehreghani, “Shift of
Pairwise Similarities for Data Clustering”, Machine Learning, 112,
2025–2051, 2023. [5] Niklas
Åkerblom, Fazeleh Sadat Hoseini, and Morteza
Haghir Chehreghani,
“Online
Learning of Network Bottlenecks via Minimax Paths”,
Machine Learning, 112: 131–150, 2023. [6] Balázs Varga, Balázs Kulcsár, and Morteza
Haghir Chehreghani, “Deep
Q-learning: a robust control approach”, International Journal of Robust
and Nonlinear Control, 33(1), pp. 526-544, 2023. [7] Arman Rahbar, Emilio Jorge, Devdatt Dubhashi,
and Morteza Haghir Chehreghani, “Do Kernel
and Neural Embeddings Help in Training and Generalization?”, Neural
Processing Letters (NPL), 55, 1681–1695, 2023. [8] Niklas
Åkerblom, and Morteza Haghir Chehreghani, “Long-Distance Electric
Vehicle Navigation using a Combinatorial Semi-Bandit Approach”, The
16th European Workshop on Reinforcement Learning (EWRL), 2023. [9] Andreas
Demetriou, Henrik Alfsvåg, Sadegh Rahrovani, and Morteza Haghir
Chehreghani, “A Deep
Learning Framework for Generation and Analysis of Driving Scenario
Trajectories”, SN Computer Science, 4, 251, 2023. [10] Ali Samadzadeh, Fatemeh Sadat Tabatabaei Far,
Ali Javadi, Ahmad Nickabadi, and Morteza Haghir Chehreghani, “Convolutional
Spiking Neural Networks for Spatio-Temporal Feature Extraction”,
Neural Processing Letters (NPL), 2023. [11] Jan Zrimec, Xiaozhi Fu, Azam SheikhMuhammad,
Christos Skrekas, Vykintas Jauniskis, Nora K. Speicher, Christoph S. Börlin,
Vilhelm Verendel, Morteza Haghir Chehreghani, Devdatt Dubhashi, Verena
Siewers, Florian David, Jens Nielsen, and Aleksej Zelezniak, “Controlling gene
expression with deep generative design of regulatory DNA”, Nature
Communications, 13, 5099, 2022. [12] Carl Johnell, and Morteza Haghir
Chehreghani, “Efficient
Optimization of Dominant Set Clustering with Frank-Wolfe Algorithms”,
31st ACM International Conference on Information and Knowledge Management
(CIKM), pp. 915–924, 2022. [Full research paper] [13] Ashkan Panahi, Arman Rahbar, Chiranjib
Bhattacharyya, Devdatt Dubhashi, and Morteza Haghir Chehreghani, “Analysis of
Knowledge Transfer in Kernel Regime”, 31st ACM International
Conference on Information and Knowledge Management (CIKM), pp. 1615–1624, 2022. [Full research paper] [14] Victor Eberstein, Jonas Sjöblom, Nikolce
Murgovski, and Morteza
Haghir Chehreghani, “A Unified
Framework for Online Trip Destination Prediction”, Machine Learning,
111, 3839–3865, 2022. [15] Sanna Jarl, Linus Aronsson,
Sadegh Rahrovani, and Morteza Haghir
Chehreghani, “Active
Learning of Driving Scenario Trajectories”, Engineering Applications of Artificial Intelligence, 113: 104972, 2022. [16] Simon Viet Johansson, Hampus Gummesson
Svensson, Esben Bjerrum, Alexander Schliep, Morteza Haghir Chehreghani,
Christian Tyrchan, and Ola Engkvist, “Using
Active Learning to Develop Machine Learning Models for Reaction Yield
Prediction”, Molecular Informatics, 41, 2200043, 2022. [17] Sara Asghari, Mostafa H. Chehreghani, and Morteza
Haghir Chehreghani, “On Using Node Indices
and Their Correlations for Fake Account Detection”, IEEE
International Conference on Big Data (IEEE BigData), 2022. [18] Hampus Gummesson Svensson, Esben Bjerrum,
Christian Tyrchan, Ola Engkvist, and Morteza Haghir Chehreghani, “Autonomous Drug Design
with Multi-Armed Bandits”, IEEE International Conference on Big Data
(IEEE BigData), 2022. [19] Mahdi Ghanbari, Mostafa Haghir Chehreghani
and Morteza Haghir Chehreghani, “Graph Clustering Using
Node Embeddings: An Empirical Study”, IEEE International Conference
on Big Data (IEEE BigData), 2022. [20] Fazeleh Sadat Hoseini, and Morteza Haghir Chehreghani, “Memory-Efficient
Minimax Distance Measures”, 26th Pacific-Asia Conference on Knowledge
Discovery and Data Mining (PAKDD), 13280, pp.
419-431, 2022. [21] Yuxin Chen, and Morteza Haghir Chehreghani,
“Trip Prediction by
Leveraging Trip Histories from Neighboring Users”, IEEE 25th International Intelligent Transportation
Systems Conference (IEEE ITSC), pp. 967-973, 2022. [22] Federica Comuni, Christopher Meszaros, Niklas
Åkerblom, and Morteza Haghir Chehreghani, “Passive and Active Learning of
Driver Behavior from Electric Vehicles”, IEEE 25th International Intelligent Transportation
Systems Conference (IEEE ITSC), pp. 929-936,
2022. [23] Hazem Peter Samoaa, Antonio Longa, Mazen
Mohamad, Morteza Haghir Chehreghani, and Philipp Leitner, “TEP-GNN:
Accurate Execution Time Prediction of Functional Tests using Graph Neural
Networks”, 23rd International Conference on Product-Focused
Software Process Improvement (PROFES), vol 13709, pp. 464–479, 2022. [Full
paper] [24] John Daniel Bossér, Erik Sörstadius, and Morteza Haghir Chehreghani, “Model-Centric
and Data-Centric Aspects of Active Learning for Deep Neural Networks”,
IEEE International Conference on Big Data (IEEE BigData), pp. 5053-5062, 2021. [25] Masoud Malek, Mostafa H. Chehreghani, Ehsan Nazerfard, and Morteza Haghir Chehreghani, “Shallow
Node Representation Learning using Centrality Indices”, IEEE International
Conference on Big Data (IEEE BigData), pp.
5209-5214, 2021. [26] Fazeleh Hoseini, Sadegh Rahrovani, and Morteza Haghir Chehreghani, “Vehicle Motion Trajectories
Clustering Via Embedding Transitive Relations”, 24rd IEEE International
Intelligent Transportation Systems Conference (IEEE ITSC), pp. 1314-1321, 2021. [27] Sanna Jarl, Julia
Wennerblom, Maria Svedlund, Sadegh Rahrovani, and Morteza Haghir Chehreghani, “Annotation
of Traffic Scenarios for AD Verification Using Active Learning”, 6th International Symposium on Future Active Safety Technology Toward
zero traffic accidents (FAST-zero), pp. 1-6, 2021. [28] Morteza
Haghir Chehreghani,
“Reliable Agglomerative
Clustering”,
International Joint Conference on Neural Networks (IJCNN),
pp. 1-8, 2021. [29] Morteza
Haghir Chehreghani,
“Unsupervised
representation learning with Minimax distance measures”, Machine Learning (MLJ), 109 (11), 2063-2097, 2020. [30] Morteza
Haghir Chehreghani, and Mostafa H. Chehreghani, “Learning representations from dendrograms”, Machine Learning (MLJ), 109 (9): 1779–1802, 2020. [31] Ashkan
Panahi, Morteza Haghir Chehreghani, and Devdatt Dubhashi, “Accelerated Proximal Incremental Algorithm
Schemes for Non-Strongly Convex Functions”, Theoretical
Computer Science, 812: 203-213, 2020. [32] Niklas
Åkerblom, Yuxin Chen, and Morteza Haghir
Chehreghani,
“An
Online Learning Framework for Energy-Efficient Navigation of Electric
Vehicles”, 29th International Joint Conference on
Artificial Intelligence (IJCAI), pp. 2051-2057, 2020. [33] Andreas
Demetriou, Henrik Alfsvåg, Sadegh Rahrovani, and Morteza
Haghir Chehreghani,
“Generation of Driving
Scenario Trajectories with Generative Adversarial Networks”,
23rd IEEE International Intelligent Transportation
Systems Conference (IEEE ITSC), 2020. [34] Erik
Thiel, Morteza Haghir Chehreghani, and Devdatt Dubhashi, “A Non-convex
Optimization Approach to Correlation Clustering”, Thirty-Third AAAI
Conference on Artificial Intelligence (AAAI), 33(01), 5159-5166, 2019. [35] Claes
Strannegård, Herman Carlström, Niklas Engsner, Fredrik Mäkeläinen, Filip
Slottner Seholm, and Morteza Haghir Chehreghani, “Lifelong
Learning Starting from Zero”,
The 12th annual conference on Artificial General Intelligence (AGI), pp.
188–197, 2019. [36] Claes
Strannegård, Herman Carlström, Niklas Engsner, Fredrik Mäkeläinen, Filip
Slottner Seholm, and Morteza Haghir Chehreghani, “Dynamic Deep Learning”, The 31st annual
workshop of the Swedish Artificial Intelligence Society (SAIS), 2019. [37] Mostafa
H. Chehreghani, and Morteza Haghir Chehreghani, “Efficient
Context-Aware K-Nearest Neighbor Search”, 40th European
Conference on Information Retrieval (ECIR), pp 466–478, 2018. [long paper] [38] Yuxin
Chen, Jean-Michel Renders, Morteza Haghir Chehreghani, and
Andreas Krause, “Efficient Online Learning
for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting”,
Thirty-Third Conference on Uncertainty in Artificial
Intelligence (UAI), 2017. (sup. here) [39] Morteza
Haghir Chehreghani,
“Classification
with Minimax Distance Measures”, Thirty-First AAAI Conference on
Artificial Intelligence (AAAI), 31(1), 2017. [40] Morteza
Haghir Chehreghani,
“Clustering by
Shift”, IEEE International Conference on Data Mining (ICDM), pp. 793-798, 2017. [41] Morteza
Haghir Chehreghani,
“Efficient
Computation of Pairwise Minimax Distance Measures”, IEEE
International Conference on Data Mining (ICDM), pp. 799-804,
2017. [42] Morteza
Haghir Chehreghani,
“Feature-Oriented
Analysis of User Profile Completion Problem”, 39th European
Conference on Information Retrieval (ECIR), pp. 304–316, 2017. [long paper] [43] Morteza
Haghir Chehreghani,
“Adaptive
Trajectory Analysis of Replicator Dynamics for Data Clustering”, Machine Learning (MLJ), 104 (2-3):
271-289, 2016. [44] Morteza
Haghir Chehreghani,
and Mostafa H. Chehreghani, “Modeling
Transitivity in Complex Networks”, Thirty-Second Conference on
Uncertainty in Artificial Intelligence (UAI), 2016. [45] Mostafa
H. Chehreghani, and Morteza Haghir Chehreghani, “Transactional
Tree Mining”, European Conference on Machine Learning and Principles
and Practice of Knowledge Discovery (ECML/PKDD), (1) 182-198, 2016. [46] Morteza
Haghir Chehreghani,
“K-Nearest
Neighbor Search and Outlier Detection via Minimax Distances”, SIAM
International Conference on Data Mining (SDM), pp. 405–413, 2016. [47] Ana
Paula Oliveira, Sotiris Dimopoulos, Alberto Giovanni Busetto, Stefan
Christen, Reinhard Dechant, Laura Falter, Morteza Haghir Chehreghani,
Szymon Jozefczuk, Christina Ludwig, Florian Rudroff, Juliane Schulz,
Alexandre Soulard, Daniele Stracka, Ruedi Aebersold, Joachim M. Buhmann,
Michael N. Hall, Matthias Peter, Uwe Sauer, and Jörg Stelling, “Inferring
causal metabolic signals that regulate the dynamic TORC1-dependent
transcriptome”, Molecular Systems
Biology,11(4): 802,
2015. [48] Ludwig
M. Busse, Morteza Haghir Chehreghani, and Joachim M. Buhmann, “Approximate
Sorting”, 35th German Conference on
Pattern Recognition (GCPR), 142-152, 2013. [49] Morteza
Haghir Chehreghani,
Ludwig M. Busse, and Joachim M. Buhmann, “Information Content in
Clustering Algorithms”, The Deutsche ArbeitsGemeinschaft Statistik
Conference (DAGStat), 2013. [50] Morteza
Haghir Chehreghani, Alberto G. Busetto, Joachim M.
Buhmann, “Information
Theoretic Model Validation for Spectral Clustering”, International
Conference on Artificial Intelligence and Statistics (AISTATS),
pp. 495-503, 2012. [51] Morteza
Haghir Chehreghani,
Mostafa H. Chehreghani, and Hassan Abolhassani, “Probabilistic
Heuristics for Hierarchical Web Data Clustering”, Computational Intelligence, 28(2):
209-233, 2012. [52] Ludwig
M. Busse, Morteza Haghir Chehreghani, Joachim M. Buhmann, “The Information Content
in Sorting Algorithms”, International Symposium on Information Theory
(ISIT), 2746-2750, 2012. [53] Alberto
G. Busetto, Morteza Haghir Chehreghani, Joachim M. Buhmann, “Approximate Set Coding for Information Theoretic Model
Validation”, The Fifth Workshop on Information Theoretic Methods in
Science and Engineering (WITMSE), pp. 15-18, 2012. [54] Joachim
M. Buhmann, Morteza Haghir Chehreghani, Mario Frank, and Andreas P.
Streich, “Information
Theoretic Model Selection for Pattern Analysis”, Journal of Machine Learning Research (JMLR)
Workshop and Conference Proceedings, extended from ICML workshop on
Unsupervised and Transfer Learning, 27:51–64, 2012.sss [55] K. H.
Brodersen, Z. Lin, A. Gupta, W.D. Penny, A.P. Leff, Morteza Haghir
Chehreghani, Alberto G. Busetto, Joachim M. Buhmann, K.E. Stephan, “Model-based
clustering using generative embedding”, Human Brain Mapping, 2012. [Oral
presentation] [recipient of Trainee Abstract
Award]. [56] Mostafa
H. Chehreghani, Morteza Haghir Chehreghani, Caro Lucas, and Masoud
Rahgozar, “OInduced:
An Efficient Algorithm for Mining Induced Patterns from Rooted Ordered Trees”, IEEE Transactions on Systems, Man, and
Cybernetics, Part A 41(5): 1013-1025, 2011. [57] Ludwig
M. Busse, Morteza Haghir Chehreghani, Joachim M. Buhmann, “Approximate
Sorting of Preference Data”, NIPS workshop on
Choice Models and Preference Learning, 2011. [selected
for NIPS workshop contributed talk] [58] Morteza
Haghir Chehreghani, Alberto G. Busetto, Joachim M. Buhmann, “Cluster
Model Validation by Maximizing Approximation Capacity”,
NIPS workshop on New Frontiers in Model Order Selection, 2011. [received NIPS travel grant] [59] Mario
Frank, Morteza Haghir Chehreghani, and Joachim M. Buhmann, “The
Minimum Transfer Cost Principle for Model-Order Selection”, European Conference
on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD),
(1) 423-438, 2011. [60] Morteza
Haghir Chehreghani,
Hassan Abolhassani, and Mostafa H. Chehreghani, “Density
link-based methods for clustering web pages”, Decision Support Systems, 47 (4): 374-382,
2009. [61] Mostafa
H. Chehreghani, Morteza Haghir Chehreghani, Masoud Rahgozar, Caro
Lucas, and Euhanna Ghadimi, “Efficient
Rule Based Structural Algorithms for Classification
of Tree-Structured Data”, Intelligent Data
Analysis, 13 (1): 165-188, 2009. [62] Morteza
Haghir Chehreghani,
Hassan Abolhassani, and Mostafa H. Chehreghani, “Improving
Density Based Methods for Hierarchical Clustering of the Web Pages”, Data and Knowledge
Engineering, 67 (1): 30-50, 2008. [63] Mehrdad
Mahdavi, Morteza Haghir Chehreghani, Hassan Abolhassani, and Rana Forsati, “Novel
Meta-Heuristic Algorithms for Clustering Web Documents”, Applied Mathematics and Computation,
201 (1-2): 441–451, 2008. [64] Mohammad
Rahimi, Hassan Abolhassani, and Morteza Haghir Chehreghani, “Improving Tree Structures to Find
Dense Clusters from Web Documents”, International
Conference on Information and Knowledge Technology (IKT), 2008 (in Persian). [65] Mostafa
H. Chehreghani, Masoud Rahgozar, Caro Lucas, and Morteza Haghir
Chehreghani, “A
Heuristic Algorithm for Clustering Rooted Ordered Trees”, Intelligent Data Analysis, 11 (4):
355-376, 2007. [66] Morteza
Haghir Chehreghani,
Hassan Abolhassani, and Mostafa H. Chehreghani “Attaining
Higher Quality for Density Based Algorithms”, International
Conference on Web Reasoning and Rule Systems (RR), LNCS, 329–338, 2007. [67] Mostafa
H. Chehreghani, Masoud Rahgozar, Caro Lucas, Morteza Haghir Chehreghani,
“Mining Maximal
Embedded Unordered Tree Patterns”, IEEE
Symposium on Computational Intelligence and Data Mining (CIDM), 437-443,
2007. [68] Morteza
Haghir Chehreghani,
Hassan Abolhassani, “H-BayesClust:
A new Hierarchical Clustering based on Bayesian Networks”, International Conference
on Advanced Data Mining and Applications (ADMA), LNCS, pp. 616–624, 2007. [69] Morteza
Haghir Chehreghani, Mohammad Rahmati, “Design and
Implementation of a 2-D Barcode based on Data Matrix Format”,
15th Iranian Conference on Electrical Engineering, 2006
(in Persian). Patents [1] Morteza
Chehreghani,
“System and method
for performing k-nearest neighbor search based on minimax distance measure
and efficient outlier detection”, Patent number:
10073887, Date of Patent: September 11, 2018. [Type: Grant] [2] Morteza Haghir Chehreghani, “Efficient Calculation of
All-Pair Path-based Distance Measures”, Patent number: 9805138, Date of Patent:
October 31, 2017. [Type: Grant] [3] Morteza Haghir Chehreghani and Yuxin Chen, “Method of Trip
Prediction by Leveraging Trip Histories from Neighboring Users”, Publication number: 20180012141,
Publication date: January 11, 2018. [Type: Application] [4] Morteza Haghir Chehreghani, “Adaptive
Trajectory Analysis of Replicator Dynamics for Data Clustering”, Publication number:
20160179923, Publication date: June 23, 2016. [Type: Application] Codes ·
An efficient method for
correlation clustering with fixed and variable number of clusters ·
Efficient
computation of Minimax distances |
|