Alumni
Ph. D. students
Zhan Gao [Mar. 2019 - Sep. 2020] I supervised Zhan during his Ph.D. time at the University of Pennsylvania with advisor Prof. Alejandro Ribeiro. Zhan worked on a mathematical framework to understand better the behavior of the graph convolutional neural network to random perturbations.
M. Sc. students
Radu Gaghi (2024) Multi-agent Reinforcement Learning for Radar Waveform Design. Together with Dr. Mario Coutino (TNO)
Alex Jeleniewski (2024) Online Adaptive Graph Neural Networks
Rodrigo Revilla Llaca (2024) Wind Power Forecasting in Wind Farms using GNNs. Together with Dr. Hadi Jamali-Rad.
Siert Sebus (2024) An Experimental Assessment of the Stability of Graph Contrastive Learning. Together with Dr. Hadi Jamali-Rad
Albert Solà Roca (2023) GGANET: Algorithm Unrolling for Water Distribution Networks Metamodeling. Together with Dr. Riccardo Taormina
Alex Möllers (2023) Bayesian Contrastive Learning on Topological Structures Together with Dr. Vincent Fortuin
Titus Naber (2023) Sparse & Interpretable Graph Attention Networks
Sneha Lodha (2023) From Clicks to Conscious Choices
Chengen Liu (2023) Simplicial Unrolling ElasticNet for Edge Flow Signal Reconstruction Together with Prof. Geert Leus
Rohan Chandrashekar (2022) Graph Regularized Tensor Decomposition for Recommender Systems Together with Dr. Kim Batselier
Simon Dahrs (2022) Pure Cold Start Recommendation by Learning on Stochastically Expanded Graphs Together with Ir. Bishwadeep Das.
Benjamin Habib (2022 cum laude) Deep Statistical Solver for Distribution System State Estimation Together with Dr. Jochen Cremer.
Raoul Kalisvaart (2022 cum laude) Nudging Towards Sustainable Choices via Recommender Systems
Gaia Zin (2021) Investigation of focal epilepsy using graph signal processing Together with Dr. Borbála Hunyadi.
Vasco de Bruijn (2021) Side-Channel Analysis with Graph Neural Networks Together with Dr. Stjepan Picek.
Matteo Pocchiari (2020) Accuracy-Diversity Trade-off in Recommender Systems Via Graph Convolutions
Tomas Sipko (2020) Identifying Author Fingerprints in Texts via Graph Neural Networks.
Maosheng Yang (2020 cum laude) Advances in Graph Signal Processing: Fast graph construction & Node-adaptive graph signal reconstruction Together with Dr. Mario Coutino and Prof. Geert Leus.
Bianca Iancu (2020 cum laude) Graph-Adaptive Activation Functions for Graph Neural Networks
Gabriele Mazzola (2020 cum laude) Graph-Time Convolutonal Neural Network: Learning from Time-Varying Signals Defined on Graph
Bishwadeep Das (2019 cum laude) Active Semi-Supervised Learning For Diffusions on Graphs Together with Prof. Geert Leus.
Ashvant Mahabir (2017) Blind Graph Topology Change Detection Together with Prof. Geert Leus.
Published theseses (and other publications with M.Sc. students)
A. Möllers, A. Immer, V. Fortuin and E. Isufi, Hodge-Aware Contrastive Learning, IEEE International Conference on Acoustic, Speech and Signal Processing, (ICASSP), South Korea, Apr. 2024. (invited paper)
C. Liu, G. Leus and E. Isufi, Unrolling of Simplicial ElasticNet for Edge Flow Signal Reconstruction, IEEE Open Journal on Signal Processing, Dec. 2023.
A. Möllers, A. Immer, E. Isufi and V. Fortuin, Uncertainty in Graph Contrastive Learning with Bayesian Neural Networks, 5th Symposium on Advances in Approximate Bayesian Inference, collocated with ICML, Jul. 2023.
A. S. Roca, A. G. Díaz, E. Isufi and R. Taormina, EPANET Metamodels with Deep Unrolling of the Global Gradient Algorithm, WSDA / CCWI Joint Conference, 2023.
B. Habib, E. Isufi, W. van Breda, A. Jongepier and J. L. Cremer, Deep Statistical Solver for Distribution System State Estimation, IEEE Transactions on Power Systems, Jun. 2023
E. Isufi, M. Pocchiari and A. Hanjalic, Accuracy-Diversity Trade-off in Recommender Systems via Graph Convolutions, Elsevier Information Processing and Management, Jul. 2020.
M. Yang, M. Coutino, G. Leus and E. Isufi, Node-Adaptive Regularization for Graph Signal Reconstruction, IEEE Open Journal of Signal Processing, 2021.
M. Yang, M. Coutino, E. Isufi and G. Leus, Node Varying Regularization for Graph Signals, EURASIP European Signal Processing Conference, Aug. 2020. (invited paper)
B. Iancu, L. Ruiz, A. Ribeiro and E. Isufi, Graph-Adaptive Activation Functions For Graph Neural Networks, IEEE International Workshop on Machine Learning for Signal Processing, Espoo, Finland, Sep. 2020.
B. Iancu and E. Isufi, Towards Finite-Time Consensus with Graph Convolutional Neural Networks, EURASIP European Signal Processing Conference (EUSIPCO), Amsterdam, The Netherlands, Aug. 2020.
E. Isufi and G. Mazzola, Graph-Time Convolutional Neural Networks, IEEE Data Science and Learning Workshop, Toronto, Ontario, Canada, Jun. 2021.
B. Das, E. Isufi and G. Leus, Active Semi-supervised Learning for Diffusions on Graphs, 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, May. 2020. (invited paper)
B. Das, E. Isufi, G. Leus, Distributed Kernel-Based Reconstruction of Graph Signals, WIC Symposium 2019. (student travel grant award)
E. Isufi, A. S. U. Mahabir and G. Leus, Blind Graph Topology Change Detection, IEEE Signal Processing Letters, vol. 15 (5), pp. 655 - 659, 2018. (presented also at ICASSP 2019)
B. Sc. honours students
Anca Badiu (2024) Hybrid Graph-based and Matrix Factorization Approach for Recommendation
Andrei Simionescu (2024) Hybrid Graph-based and Matrix Factorization Approach for Recommendation
B. Sc. students
Research Projects @ TU Delft
Rauno Arike (2024) A Beyond Spectral Graph Theory: An Explainability-Driven Approach to Analysis the Stability of GNNs to Topology Perturbations
Yigit Colakoglu (2024) An Experimental Look at the Stability of GNNs Againts Topological Perturbations
Khoa Nguyen (2024) Investigation of Stability Property of GNN Architectures Under Domain Perturbation
Vladimir Rullens (2024) The Impact of GNN Task Types on the Stability of GNNs in Face of Perturbations
Alex Brown (2024) Stability of GNNs w.r.t. Different Types of Topological Perturbations
Melle Koper (2022) Item-Item Collaborative Filtering via Graph Regularization
Karolis Mariunas (2022) Performance of Total Variation Regularizer for User Collaborative Filtering
Sérénic Monté (2022) Tikhonov and Sobolev regularizers compared to user-based KNN collaborative filtering
Lars van Blokland (2022) Total Variation Regularization for Item KNN Collaborative Filtering: Performance Analysis
Kevin Zhu (2022) Predicting Micro-Earthquakes with Deep Neural Networks
Glenn van den Belt (2022) Short-term Earthquake Prediction with Deep Neural Networks
Pijus Krisiukenas(2022) Impact of Focal Depth on Short-Term Earthquake Prediction using Deep Learning
Amaury Charlot (2022) How long before strike can we predict earthquakes with an LSTM neural network?
Gancho Georgiev (2022) Impact of seismic wavelength to detect high-magnitude earthquakes via deep learning
Irtaza Hashmi (2022) How does a CNN mixes with LSTM methods compare with the individual one in predicting earthquakes?
Daniel van den Akker (2022) Earthquake prediction: An MLP & SVM Comparison
Maikel Houbaer (2022) Comparing Multichannel Mixed CNN-RNN to individual models for earthquake prediction
Xiangyu Du (2022) Short-term Earthquake Prediction via Recurrent Neural Network Models
Visitors
Samuel Rey Escudero [June 2024] Samuel is a visiting assistant professor from the King Juan Carlos University in Spain. He is working on graph-based learning over directed acyclic graphs.
Madeline Navarro [June 2024] Madeline is a visiting Ph.D. student from the Rice University in the United States. She is working on data augmentation and fairness for graphs and topologies.
Victor M. Tenorio [May 2024] Victor is a visiting Ph.D. student from the King Juan Carlos University in Spain. He is working on machine learning for higher-order networks.
Andrei Buciulea Vlas [June 2023] Andrei is a visiting Ph.D. student from the King Juan Carlos University in Spain. He is working on topology identification on higher-order networks.
Kaiwen Zhang [September 2020] Kaiwen was a visitor student working on sampling strategies for graph signals.
Oxana Rimleanscaia [December 2019] Oxana visited the Multimedia Computing Group to work on her M. Sc. degree from the University of Perugia. Her work was based on design of rational graph filters via Chebyshev rational functions.
Alberto Natali [June 2019] Alberto visited the Circutis and Systems Group after his M. Sc. degree from the University of Perugia under the Erasmus+ program. Alberto worked on forecasting techniques for graph-based data. (now: Ph. D. student, TU Delft)