Lab Image Machine Learning & Decision Making Lab Chalmers Image

Home Team Teaching Publications Patents Code



Home

The Machine Learning and Decision Making Lab (ML&DM Lab) is based in the Data Science and AI division in the Department of Computer Science and Engineering (CSE) at Chalmers University of Technology, Gothenburg, Sweden. The lab, led by Morteza Haghir Chehreghani, conducts research in different areas of machine learning and AI-enabled decision making.

Our research spans both the foundations of machine learning and decision making as well as real-world applications, aiming to push the boundaries of machine learning while addressing practical challenges across diverse domains such as transport, energy, life sciences, autonomous systems, recommendation systems, and decision support systems. Our current research focuses on the following topics:

Our research is supported by Swedish Research Council (VR), Vinnova, and WASP (Wallenberg AI, Autonomous Systems and Software Program).

Swedish Research Council Vinnova Wallenberg AI, Autonomous Systems and Software Program (WASP)



Team

Group Leader

Morteza Haghir Chehreghani

Morteza Haghir Chehreghani
Professor

Morteza is a Professor of Machine Learning in the Data Science and AI division, Department of Computer Science and Engineering, Chalmers University of Technology, where he leads the Machine Learning and Decision Making Lab (ML&DM Lab). Morteza received his Ph.D. in Computer Science from ETH Zurich, Switzerland, in 2014, under the supervision of Prof. Dr. Joachim M. Buhmann at the Institute for Machine Learning. Following his Ph.D., he spent about four years as a researcher at Naver Labs Europe (formerly known as Xerox Research Centre Europe) in the Machine Learning and Optimization team, where he held positions as Staff Research Scientist I and II. Morteza joined Chalmers University of Technology in 2018 as an Associate Professor and became a Professor in 2024. He is also an affiliated faculty member of Wallenberg AI, Autonomous Systems and Software Program (WASP) and Chalmers AI Research (CHAIR), as well as a member of ELLIS – the European Laboratory for Learning and Intelligent Systems.


PhD Students




Linus Aronsson
Active Learning, Correlation Clustering, Deep Learning




Hampus Gummesson Svensson
Reinforcement Learning, Multi-Armed Bandits, Drug Discovery




Deepthi Pathare
Reinforcement Learning, Large Language Models (LLMs), Transport




Jack Sandberg
Multi-Armed Bandits, Reinforcement Learning, Gaussian Processes




Valter Schütz
Reinforcement Learning, Large Language Models (LLMs)

Affiliated PhD Students




Hannes Nilsson
Online Learning, Uncertainty-Aware Learning, Energy Models




Kilian Tamino Freitag
Reinforcement Learning, Deep Learning, Robotics

Alumni




Teaching

Morteza Haghir Chehreghani is the examiner and teacher of the following courses:

The other teaching activities at Chalmers include:




Publications

  1. Information-Theoretic Active Correlation Clustering

  2. Learning for routing: A guided review of recent developments and future directions

  3. Diversity-Aware Reinforcement Learning for de novo Drug Design

  4. Bayesian Analysis of Combinatorial Gaussian Process Bandits

  5. Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach

  6. Diesel Combustion Parameter Estimation via Machine Learning – A Comparative Study

  7. Mining Transactional Tree Databases under Homeomorphism

  8. Tree Ensembles for Contextual Bandits

  9. Hierarchical Correlation Clustering and Tree Preserving Embedding

  10. Correlation Clustering with Active Learning of Pairwise Similarities

  11. Utilizing Reinforcement Learning for de novo Drug Design

  12. Online Learning Models for Vehicle Usage Prediction During COVID-19

  13. De novo generated combinatorial library design

  14. A contextual combinatorial semi-bandit approach to network bottleneck identification

  15. A unified active learning framework for annotating graph data for regression tasks

  16. Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework

  17. Efficient Online Decision Tree Learning with Active Feature Acquisition

  18. Online Learning of Energy Consumption for Navigation of Electric Vehicles

  19. A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles

  20. Online Learning of Network Bottlenecks via Minimax Paths

  21. Shift of Pairwise Similarities for Data Clustering

  22. Deep Q-learning: a robust control approach

  23. Do Kernel and Neural Embeddings Help in Training and Generalization?

  24. Long-Distance Electric Vehicle Navigation using a Combinatorial Semi-Bandit Approach

  25. Batch Mode Deep Active Learning for Regression on Graph Data

  26. Diverse Data Expansion with Semi-Supervised k-Determinantal Point Processes

  27. Non-Uniform Sampling Methods for Large Itemset Mining

  28. Improved Tactical Decision Making and Control Architecture for Autonomous Truck in SUMO Using Reinforcement Learning

  29. A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories

  30. Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction

  31. Controlling gene expression with deep generative design of regulatory DNA

  32. Efficient Optimization of Dominant Set Clustering with Frank-Wolfe Algorithms

  33. Analysis of Knowledge Transfer in Kernel Regime

  34. A Unified Framework for Online Trip Destination Prediction

  35. Active Learning of Driving Scenario Trajectories

  36. Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction

  37. On Using Node Indices and Their Correlations for Fake Account Detection

  38. Autonomous Drug Design with Multi-Armed Bandits

  39. Graph Clustering Using Node Embeddings: An Empirical Study

  40. Memory-Efficient Minimax Distance Measures

  41. Trip Prediction by Leveraging Trip Histories from Neighboring Users

  42. Passive and Active Learning of Driver Behavior from Electric Vehicles

  43. TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networks

  44. Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks

  45. Shallow Node Representation Learning using Centrality Indices

  46. Vehicle Motion Trajectories Clustering Via Embedding Transitive Relations

  47. Annotation of Traffic Scenarios for AD Verification Using Active Learning

  48. Reliable Agglomerative Clustering

  49. Unsupervised representation learning with Minimax distance measures

  50. Learning representations from dendrograms

  51. Accelerated Proximal Incremental Algorithm Schemes for Non-Strongly Convex Functions

  52. An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles

  53. Generation of Driving Scenario Trajectories with Generative Adversarial Networks

  54. A Non-convex Optimization Approach to Correlation Clustering

  55. Lifelong Learning Starting from Zero

  56. Dynamic Deep Learning

  57. Efficient Context-Aware K-Nearest Neighbor Search

  58. Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting

  59. Classification with Minimax Distance Measures

  60. Clustering by Shift

  61. Efficient Computation of Pairwise Minimax Distance Measures

  62. Feature-Oriented Analysis of User Profile Completion Problem

  63. Adaptive Trajectory Analysis of Replicator Dynamics for Data Clustering

  64. Modeling Transitivity in Complex Networks

  65. Transactional Tree Mining

  66. K-Nearest Neighbor Search and Outlier Detection via Minimax Distances

  67. Inferring causal metabolic signals that regulate the dynamic TORC1-dependent transcriptome

  68. Approximate Sorting

  69. Information Content in Clustering Algorithms

  70. Information Theoretic Model Validation for Spectral Clustering

  71. Probabilistic Heuristics for Hierarchical Web Data Clustering

  72. The Information Content in Sorting Algorithms

  73. Approximate Set Coding for Information Theoretic Model Validation

  74. Information Theoretic Model Selection for Pattern Analysis

  75. Model-based clustering using generative embedding

  76. OInduced: An Efficient Algorithm for Mining Induced Patterns from Rooted Ordered Trees

  77. Approximate Sorting of Preference Data

  78. Cluster Model Validation by Maximizing Approximation Capacity

  79. The Minimum Transfer Cost Principle for Model-Order Selection

  80. Density link-based methods for clustering web pages

  81. Efficient Rule Based Structural Algorithms for Classification of Tree-Structured Data

  82. Improving Density Based Methods for Hierarchical Clustering of the Web Pages

  83. Novel Meta-Heuristic Algorithms for Clustering Web Documents

  84. Improving Tree Structures to Find Dense Clusters from Web Documents

  85. A Heuristic Algorithm for Clustering Rooted Ordered Trees

  86. Attaining Higher Quality for Density Based Algorithms

  87. Mining Maximal Embedded Unordered Tree Patterns

  88. H-BayesClust: A new Hierarchical Clustering based on Bayesian Networks

  89. Design and Implementation of a 2-D Barcode based on Data Matrix Format and Reed-Solomon Error Correcting Codes



Patents

  1. Method and computer system for multi-level control of motion actuators in an autonomous vehicle

  2. System and method for performing k-nearest neighbor search based on minimax distance measure and efficient outlier detection

  3. Efficient Calculation of All-Pair Path-based Distance Measures

  4. Method of Trip Prediction by Leveraging Trip Histories from Neighboring Users

  5. Adaptive Trajectory Analysis of Replicator Dynamics for Data Clustering



Code & Data