ESANN 2021 programme

Wednesday, 06.10.2021

09:00
Welcome session
 
09:10
Federated Learning – Methods, Applications and Beyond
Organized by: Frank-Michael Schleif, Fabrice Rossi, Christoph Raab, Moritz Heusinger
09:10
Federated Learning - Methods, Applications and beyond
  • Moritz Heusinger, University of Applied Sciences Würzburg-Schweinfurt (Germany)
  • Christoph Raab, University of Applied Science Würzburg-Schweinfurt (Germany)
  • Fabrice Rossi, CEREMADE - Université Paris Dauphine PSL (France)
  • Frank-Michael Schleif, University of Applied Sciences Würzburg-Schweinfurt (Germany)
09:30
Privacy-Preserving Kernel Computation For Vertically Partitioned Data
  • Mirko Polato, University of Padova (Italy)
  • Alberto Gallinaro, University of Padova (Italy)
  • Fabio Aiolli, University of Padova (Italy)
09:50
Decay Momentum for Improving Federated Learning
  • Miguel Fernandes, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Catarina Silva, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Joel Arrais, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Alberto Cardoso, University of Coimbra, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Bernardete Ribeiro, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
10:10
Federated Learning – Methods, Applications and Beyond - poster spotlights
Organized by: Frank-Michael Schleif, Fabrice Rossi, Christoph Raab, Moritz Heusinger
10:10
Continual Learning at the Edge: Real-Time Training on Smartphone Devices
  • Lorenzo Pellegrini, University of Bologna (Italy)
  • Vincenzo Lomonaco, University of Pisa (Italy)
  • Gabriele Graffieti, University of Bologna (Italy)
  • Davide Maltoni, University of Bologna (Italy)
10:11
Federated Learning Vector Quantization
  • Johannes Brinkrolf, CITEC - Cognitive Interaction Technology Bielefeld University (Germany)
  • Barbara Hammer, CITEC - Bielefeld University (Germany)
10:12
Coffee break
 
10:30
Evaluation metrics, and concept drift
10:30
Judging competitions and benchmarks: a candidate election approach
  • Adrien Pavao, Université Paris-Saclay (France)
  • Isabelle Guyon, Université Paris-Saclay (France)
  • Michael Vaccaro, Université Paris-Saclay (France)
10:50
Concept Drift Segmentation via Kolmogorov-Trees
  • Fabian Hinder, Cognitive Interaction Technology (CITEC), Bielefeld University (Germany)
  • Barbara Hammer, Cognitive Interaction Technology (CITEC), Bielefeld University (Germany)
11:10
Investigating Intensity and Transversal Drift in Hyperspectral Imaging Data
  • Valerie Vaquet, CITEC, Bielefeld University (Germany)
  • Patrick Menz, Fraunhofer Institute of Factory Operation and Automation (IFF) (Germany)
  • Udo Seiffert, Fraunhofer IFF Magdeburg (Germany)
  • Barbara Hammer, Cognitive Interaction Technology (CITEC), Bielefeld University (Germany)
11:30
Predicting employee attrition with a more effective use of historical events
  • Abdel-Rahmen Korichi, Université de Lyon (France)
  • Hamamache Kheddouci, Université de Lyon (France)
  • Daniel West, Panalyt (Singapore)
11:50
Evaluation metrics, and concept drift - poster spotlights
11:50
Enhash: A Fast Streaming Algorithm For Concept Drift Detection
  • Aashi Jindal, IIT Delhi (India)
  • Prashant Gupta, IIT Delhi (India)
  • Debarka Sengupta, IIIT Delhi (India)
  • Jayadeva Jayadeva, IIT Delhi (India)
11:51
Lifelong Learning from Event-based Data
  • Vadym Gryshchuk, University of Hamburg (Germany)
  • Cornelius Weber, University of Hamburg , Department of Informatics (Germany)
  • Chu Kiong Loo, University of Malaya, Department of Artificial Intelligence, Faculty of Computer Science and Information Technology (Malaysia)
  • Stefan Wermter, University of Hamburg , Department of Informatics (Germany)
11:52
Sample efficient localization and stage prediction with autoencoders
  • Sebastian Hoch, Institute for Machine Learning and Analytics - Offenburg University (Germany)
  • Sascha Lange, PSIORI GmbH (Germany)
  • Janis Keuper, Institute for Machine Learning and Analytics - Offenburg University (Germany)
11:53
Transfer learning in Bayesian optimization for the calibration of a beam line in proton therapy
  • Valentin Hamaide, UCLouvain (Belgique)
  • François Glineur, UCLouvain (Belgique)
11:54
Domain Adversarial Tangent Learning Towards Interpretable Domain Adaptation
  • Christoph Raab, University of Applied Science Würzburg-Schweinfurt (Germany)
  • Sascha Saralajew, Bosch Center for Artificial Intelligence (Germany)
  • Frank-Michael Schleif, University of Applied Sciences Würzburg-Schweinfurt (Germany)
11:55
Demo: how to use gather.town ?
 
12:00
Lunch break
 
13:30
Deep learning for graphs
Organized by: Davide Bacciu, Filippo Maria Bianchi, Benjamin Paassen, Cesare Alippi
13:30
Deep learning for graphs
  • Davide Bacciu, Università di Pisa (Italy)
  • Filippo Maria Bianchi, NORCE - the Norwegian Research Center (Norway)
  • Benjamin Paassen, The University of Sydney (Australia)
  • Cesare Alippi, Università della Svizzera italiana (Switzerland)
13:50
Dynamic Graph Echo State Networks
  • Domenico Tortorella, University of Pisa (Italy)
  • Alessio Micheli, Università di Pisa (Italy)
14:10
Improving Graph Variational Autoencoders with Multi-Hop Simple Convolutions
  • Erik Jhones Freitas do Nascimento, Instituto Federal de Educação, Ciência e Tecnologia do Ceará (IFCE) (Brazil)
  • Amauri Souza, Federal Institute of Ceara (Brazil) (Brazil)
  • Diego Mesquita, Aalto University (A?) (Finland)
14:30
Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting
  • Luca Hermes, Bielefeld University CoR-Lab (CITEC) (Germany)
  • Barbara Hammer, CITEC - Bielefeld University (Germany)
  • Malte Schilling, Machine Learning Group, Bielefeld University (Germany)
14:50
Deep learning for graphs - poster spotlights
Organized by: Davide Bacciu, Filippo Maria Bianchi, Benjamin Paassen, Cesare Alippi
14:50
Tangent Graph Convolutional Network
  • Luca Pasa, University of Padova, Italy (Italy)
  • Nicolò Navarin, University of Padua (Italy)
  • Alessandro Sperduti, University of Padua (Italy)
14:51
Transformers for Molecular Graph Generation
  • Tim Cofala, University of Oldenburg (Germany)
  • Oliver Kramer, University of Oldenburg (Germany)
14:52
Inductive learning for product assortment graph completion
  • Marco Trincavelli, H&M Group AB (Sweden)
  • Haris Dukic, Universitá di Pisa (Italy)
  • Georgios Deligiorgis, H&M Group AB (Sweden)
  • Pierpaolo Sepe, Universitá di Pisa (Italy)
  • Davide Bacciu, Universitá di Pisa (Italy)
15:10
Deep learning and image processing
15:10
Evolutionary Deep Multi-Task Learning
  • Oliver Kramer, University of Oldenburg (Germany)
15:30
Semantic Prediction: Which One Should Come First, Recognition or Prediction?
  • Hafez Farazi, University of Bonn (Germany)
  • Jan Nogga, University of Bonn (Germany)
  • Sven Behnke, University of Bonn (Germany)
15:50
Deep Graph Convolutional Networks for Wind Speed Prediction
  • Tomasz Stańczyk, Maastricht University, Department of Data Science and Knowledge Engineering, Paul-Henri Spaaklaan 1, 6229 EN Maastricht, The Netherlands (Netherlands)
  • Siamak Mehrkanoon, Maastricht University (The Netherlands)
16:10
Deep learning and image processing - poster spotlights
16:10
Benign overfitting of fully connected Deep Nets:A Sobolev space viewpoint
  • Stephane Chretien, Université Lyon 2, Laboratoire ERIC (France)
  • Emmanuel Caron-Parte, University of Avignon Laboratoire de Mathématiques d'Avignon (France)
16:11
Correlated Weights Neural Layer with external control
  • Slawomir Golak, Silesian University of Technology (Politechnika Slaska) (Poland)
16:12
Comprehensive Analysis of the Screening of COVID-19 Approaches in Chest X-ray Images from Portable Devices
  • Daniel Iglesias, University of A Coruña (Spain)
  • Joaquim de Moura, University of A Coruña (Spain)
  • Jorge Novo, University of A Coruña (Spain)
  • Marcos Ortega, University of A Coruña (Spain)
16:13
Data-Efficient Training of High-Resolution Images in Medical Domain
  • Shruti Kunde, TCS (India)
  • Amey Pandit, TCS (India)
  • Kushagra Mahajan
  • Monika Sharma, Tata Consultancy Services (India)
  • Rekha Singhal, TCS (India)
  • Lovekesh Vig, Tata Consultancy Services (India)
16:14
CAS-Net: A Novel Coronary Artery Segmentation Neural Network
  • Rawaa Hamdi, Laboratory of Technology and Medical Imaging, Faculty of Medicine, University of Monastir, Tunisia (Tunisie)
  • Asma Kerkeni
  • Mouhamed hédi Bedoui
  • Asma Ben Abdallah
16:16
Improved and Generalized Vine Line Detection on Aerial Images Using Asymmetrical Neural Networks and ML Subclassifiers
  • Jérôme Treboux, HES-SO Valais-Wallis (Switzerland)
  • Rolf Ingold, University of Fribourg (Switzerland)
  • Dominique Genoud, HES-SO Valais-Wallis (Switzerland)
16:17
Cross-modal verification for 3D object detection
  • Haodi ZHANG, LITIS Lab, INSA ROUEN (France)
  • Alexandrina Rogozan, LITIS - INSA Rouen Normandie (France)
  • Abdelaziz Bensrhair, LITIS - INSA Rouen Normandie (France)
16:18
Fourier-based Video Prediction through Relational Object Motion
  • Malte Mosbach, University of Bonn, Computer Science Institute VI, Autonomous Intelligent Systems (Germany)
  • Sven Behnke, University of Bonn (Germany)
16:19
Object Detection on Thermal Images: Performance of YOLOv4 Trained on Small Datasets
  • Maxence Chaverot, NT2I (FRANCE)
  • Maxime Carré, NT2I (France)
  • Michel Jourlin, Hubert Curien Laboratory (France)
  • Abdelaziz Bensrhair, LITIS - INSA Rouen Normandie (France)
  • Richard Grisel, INSA Rouen Normandie (France)
16:20
Temperature as a Regularizer for Semantic Segmentation
  • Chanho Kim, University of Ottawa (Canada)
  • Won-Sook Lee, University of Ottawa (Canada)
16:21
Poster exhibition
 
18:00
End of first day
 

Thursday, 07.10.2021

09:00
Machine Learning for Measuring and Analyzing Online Social Communications
Organized by: Chris Bronk, Amaury Lendasse, Peggy Lindner, Dan S. Wallach, Barbara Hammer
09:00
Machine Learning for Measuring and Analyzing Online Social Communications
  • Chris Bronk, University of Houston (USA)
  • Amaury Lendasse, University of Houston (USA)
  • Peggy Lindner, University of Houston (USA)
  • Dan S. Wallach, Rice University (USA)
  • Barbara Hammer, CITEC - Bielefeld University (Germany)
09:20
Toxicity Detection in Online Comments with Limited Data: A Comparative Analysis
  • Max Lübbering, Fraunhofer IAIS (Germany)
  • Maren Pielka, Fraunhofer IAIS (Germany)
  • Kajaree Das, University of Bonn (Germany)
  • Michael Gebauer, Technische Universität Berlin (Germany)
  • Rajkumar Ramamurthy, Fraunhofer IAIS (Germany)
  • Christian Bauckhage, Fraunhofer IAIS & Fraunhofer Center for Machine Learning (Deutschland)
  • Rafet Sifa, Fraunhofer IAIS & Fraunhofer Center for Machine Learning (Deutschland)
09:40
Machine Learning for Measuring and Analyzing Online Social Communications - poster spotlights
Organized by: Chris Bronk, Amaury Lendasse, Peggy Lindner, Dan S. Wallach, Barbara Hammer
09:40
Emotional Intensity Level Analysis of Speech Emotional Intensity Estimation
  • Megumi Kawase, Tokyo Institute of Technology (Japan)
  • Minoru Nakayama, Tokyo Institute of Technology (Japan)
09:41
Natural language processing - poster spotlights
09:41
Weightless Neural Networks for text classification using tf-idf
  • Antonio Sorgente, Istituto di Scienze Applicate e Sistemi Intelligenti – CNR (Italia)
  • Massimo De Gregorio, CNR (Italy)
  • Giuseppe Vettigli, Centrica plc (United Kingdom)
09:42
End-to-end Keyword Spotting using Xception-1d
  • Juan Gómez-Sanchis, University of Valencia, Intelligent Data Analysis Laboratory (IDAL) (Spain)
  • Juan Gómez-Sanchis
  • Marcelino Martinez-Sober
  • Joan Vila-Francés
  • Antonio-José Serrano López
  • Emilio Soria Olivas, Please complete (please complete)
09:43
Unsupervised Word Representations Learning with Bilinear Convolutional Network on Characters
  • Thomas Luka, Ecole des Ponts (France)
  • Laure Soulier, Sorbonne Université (France)
  • David Picard, Ecole des Ponts (France)
09:44
TSR-DSAW: Table Structure Recognition via Deep Spatial Association of Words
  • Arushi Jain, Tata Consultancy Services (India)
  • Shubham Paliwal, Tata Consultancy Services (India)
  • Monika Sharma, Tata Consultancy Services (India)
  • Lovekesh Vig, Tata Consultancy Services (India)
09:45
Sparse mixture of von Mises-Fisher distribution
  • Florian Barbaro, Université Paris 1 Panthéon-Sorbonne - Laboratoire SAMM EA 4543 (France)
  • Fabrice Rossi, CEREMADE - Université Paris Dauphine PSL (France)
09:46
Towards Robust Auxiliary Tasks for Language Adaptation
  • Gil Rocha, Artificial Intelligence and Computer Science Laboratory (LIACC) Faculty of Engineering, University of Porto (FEUP) (Portugal)
  • Henrique Lopes Cardoso, Artificial Intelligence and Computer Science Laboratory (LIACC) Faculty of Engineering, University of Porto (FEUP) (Portugal)
09:47
Coffee break
 
10:00
Recurrent learning, and reinforcement learning
10:00
Continual Learning with Echo State Networks
  • Andrea Cossu, University of Pisa (Italy)
  • Davide Bacciu, Università di Pisa (Italy)
  • Antonio Carta, University of Pisa (Italy)
  • Claudio Gallicchio, University of Pisa (Italy)
  • Vincenzo Lomonaco, University of Pisa (Italy)
10:20
RecLVQ: Recurrent Learning Vector Quantization
  • Jensun Ravichandran, University of Applied Sciences Mittweida, Saxon Institute for Computational Intelligence and Machine Learning (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida, Saxon Institute for Computational Intelligence and Machine Learning (Deutschland)
  • Marika Kaden, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Germany)
10:40
Improvement on Generative Adversarial Network for Targeted Drug Design
  • Beatriz P. Santos, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Maryam Abbasi, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC), University of Coimbra, Coimbra, Portugal. (Portugal)
  • Tiago Pereira, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Bernardete Ribeiro, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Joel Arrais, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
11:00
Reservoir Computing by Discretizing ODEs
  • Claudio Gallicchio, University of Pisa (Italy)
11:20
Constraint optimization for Echo State Networks applied to satellite image forecasting
  • Jochen J. Steil, TU Braunschweig (Germany)
  • Yannic Lieder, TU Braunschweig (Germany)
11:40
Deep Echo State Networks for Functional Ambulation Categories Estimation
  • Luca Pedrelli, Scuola Superiore Sant’Anna, Pisa, Italy. (Italy)
  • E. Bergamini, University of Rome "Foro Italico" (Italia)
  • Marco Tramontano, Fondazione Santa Lucia IRCCS (Italy)
  • Giuseppe Vannozzi, University of Rome Foro Italico (Italy)
  • Andrea Mannini, Scuola Superiore Sant'Anna (Italy)
12:00
Recurrent learning, and reinforcement learning - poster spotlights
12:00
An Algorithmic Approach to Establish a Lower Bound for the Size of Semiring Neural Networks
  • Martin Böhm, Universität Leipzig (Germany)
  • Thomas Schmid, Lancaster University (Germany)
12:01
Echo-state neural networks forecasting steelworks off-gases for their dispatching in CH4 and CH3OH syntheses reactors
  • Ismael Matino, Scuola Superiore Sant’Anna TeCIP Institute, ICT-COISP (Italy)
  • Stefano Dettori, Scuola Superiore Sant’Anna ­ TeCIP Institute, ICT-COISP (Italy)
  • Valentina Colla, Scuola Superiore Sant’Anna ­ TeCIP Institute, ICT-COISP (Italy)
  • Katharina Rechberger, K1-MET GmbH (Austria)
  • Nina Kieberger, voestalpine Stahl GmdH, Research and Development Ironmaking, Technical Department, Business Unit Slab (Austria)
12:02
Deep Learning Model for Context-Dependent Survival Analysis
  • Raphaël Langhendries, Université Paris I - SAMM & Safran Aircraft Engines (France)
  • Jérôme Lacaille, Datalab, Safran Aircraft Engines (France)
12:03
Behavior Constraining in Weight Space for Offline Reinforcement Learning
  • Phillip Swazinna, Siemens AG / TU Munich (Germany)
  • Steffen Udluft, Siemens Technology (Germany)
  • Daniel Hein, Siemens AG (Germany)
  • Thomas Runkler, Siemens AG/ TU Munich (Germany)
12:04
Multiobjective Reinforcement Learning in Optimized Drug Design
  • Maryam Abbasi, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC), University of Coimbra, Coimbra, Portugal. (Portugal)
  • Tiago Pereira, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Beatriz P. Santos, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Bernardete Ribeiro, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Joel Arrais, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
12:05
Density Independent Self-organized Support for Q-Value Function Interpolation in Reinforcement Learning
  • Antonin Calba, Université de Lorraine (France)
  • Alain Dutech, INRIA (France)
  • Jeremy Fix, CentraleSupelec (France)
12:06
Lunch break
 
13:30
Complex Data: Learning Trustworthily, Automatically, and with Guarantees
Organized by: Luca Oneto, Nicolò Navarin, Battista Biggio, Federico Errica, Alessio Micheli, Franco Scarselli, Monica Bianchini, Alessandro Sperduti
13:30
Complex Data: Learning Trustworthily, Automatically, and with Guarantees
  • Luca Oneto, University of Genoa (Italy)
  • Nicolò Navarin, University of Padua (Italy)
  • Battista Biggio, University of Cagliari (Italy)
  • Federico Errica, Università di Pisa (Italy)
  • Alessio Micheli, Università di Pisa (Italy)
  • Franco Scarselli, SAILAB - University of Siena (Italy)
  • Monica Bianchini, SAILAB - University of Siena (Italy)
  • Alessandro Sperduti, University of Padua (Italy)
13:50
The Benefits of Adversarial Defence in Generalisation
  • Luca Oneto, University of Genoa (Italy)
  • Sandro Ridella, University of Genoa (Italy)
  • Davide Anguita, DIBRIS - University of Genova (Italy)
14:10
Slope: A First-order Approach for Measuring Gradient Obfuscation
  • Maura Pintor, University of Cagliari (Italy)
  • Luca Demetrio, University of Cagliari (Italy)
  • Giovanni Manca, University of Cagliari (Italy)
  • Battista Biggio, University of Cagliari (Italy)
  • Fabio Roli, University of Cagliari (Italy)
14:30
Complex Data: Learning Trustworthily, Automatically, and with Guarantees - poster spotlights
Organized by: Luca Oneto, Nicolò Navarin, Battista Biggio, Federico Errica, Alessio Micheli, Franco Scarselli, Monica Bianchini, Alessandro Sperduti
14:30
Robust Malware Classification via Deep Graph Networks on Call Graph Topologies
  • Federico Errica, Università di Pisa (Italy)
  • Giacomo Iadarola, Institute of Informatics and Telematics, National Research Council of Italy (Italy)
  • Fabio Martinelli, Institute of Informatics and Telematics, National Research Council of Italy
  • Francesco Mercaldo, University of Molise, Department of Medicine and Health Sciences
  • Alessio Micheli, Università di Pisa (Italy)
14:31
Boundary-Based Fairness Constraints in Decision Trees and Random Forests
  • Géraldin Nanfack, University of Namur (Belgium)
  • Valentin Delchevalerie, University of Namur (Belgium)
  • Benoit Frénay, Université de Namur (Belgium)
14:32
Model selection - poster spotlights
14:32
NNBMSS: a Novel and Fast Method for Model Structure Selection
  • Amaury Lendasse, University of Houston (USA)
  • Kallin Khan, Edammo Inc (USA)
  • Edward Ratner, Edammo Inc (USA)
14:33
Pruning Neural Networks with Supermasks
  • Vincent Rolfs, Universität Hamburg
  • Matthias Kerzel, Universität Hamburg (Germany)
  • Stefan Wermter, University of Hamburg , Department of Informatics (Germany)
14:34
Compact Neural Architecture Search for Local Climate Zones Classification
  • Kalifou Rene Traore, German Aerospace Center (DLR) & Technical University of Munich (TUM) (Germany)
  • Andrés Camero, German Aerospace Center (DLR) (Germany)
  • Xiao Xiang Zhu, German Aerospace Center (DLR) & Technical University of Munich (TUM) (Germany)
14:35
Coffee break
 
14:50
Unsupervised learning
14:50
Anomalous Cluster Detection in Large Networks with Diffusion-Percolation Testing
  • Corentin Larroche, Télécom Paris (France)
  • Johan Mazel, ANSSI (France)
  • Stéphan Clémençon, Telecom Paris (France)
15:10
Calliope - A Polyphonic Music Transformer
  • Andrea Valenti, Università di Pisa (Italy)
  • Stefano Berti, University of Pisa (Italy)
  • Davide Bacciu, Universitá di Pisa (Italy)
15:30
Dynamic clustering and modeling of temporal data subject to common regressive effects
  • Louise Bonfils, Université Gustave Eiffel (France)
  • Allou Same, Université Gustave Eiffel (France)
  • Latifa Oukhellou, Université Gustave Eiffel (France)
15:50
Stochastic quartet approach for fast multidimensional scaling
  • Pierre Lambert, UCLouvain (Belgium)
  • Cyril de Bodt, UCLouvain - ICTEAM (Belgium)
  • Michel Verleysen, UCLouvain - ICTEAM institute (Belgium)
  • John Lee, UCLouvain (Belgium)
16:10
Unsupervised learning - poster spotlights
16:10
Federated Learning approach for SpectralClustering
  • Elena Hernández-Pereira, Universidade da Coruña (Spain)
  • Oscar Fontenla-Romero, Universidade da Coruña (Spain)
  • Bertha Guijarro-Berdiñas, Universidade da Coruña (Spain)
  • Beatriz Pérez Sánchez, Universidade da Coruña (Spain)
16:11
Validating static call graph-based malware signatures using community detection methods
  • Attila Mester, Babes-Bolyai University (Romania)
  • Zalán Bodó, Babes-Bolyai University, Faculty of Mathematics and Computer Science (Romania)
16:12
Impact of data subsamplings in Fast Multi-Scale Neighbor Embedding.
  • Pierre Lambert, UCLouvain (Belgium)
  • John Lee, UCLouvain (Belgium)
  • Michel Verleysen, UCLouvain - ICTEAM institute (Belgium)
  • Cyril de Bodt, UCLouvain - ICTEAM (Belgium)
16:13
Semi-supervised learning with Bayesian Confidence Propagation Neural Network
  • Naresh Balaji Ravichandran, KTH Royal Institute of Technology (Sweden)
  • Anders Lansner, Stockholm University and KTH Royal Institute of Technology (Sweden)
  • Pawel Herman, KTH Royal Institute of Technology (Sweden)
16:14
Combining Attack Success Rate and DetectionRate for effective Universal Adversarial Attacks
  • Valentina Poggioni, University of Perugia, Italy (Italy)
  • Alina Elena Baia, University of Perugia (Italy)
  • Alfredo Milani, University of Perugia (Italy)
16:15
Poster exhibition
 
18:00
End of second day
 

Friday, 08.10.2021

09:00
Machine learning and data mining for urban mobility intelligence
Organized by: Etienne Come, Latifa Oukhellou, Allou Same, Lijun Sun
09:00
Machine learning and data mining for urban mobility intelligence
  • Etienne Come, Univ Gustave Eiffel (France)
  • Latifa Oukhellou, Université Gustave Eiffel (France)
  • Allou Same, Université Gustave Eiffel (France)
  • Lijun Sun, McGill University (Canada)
09:20
Multivariate Time Series Multi-Coclustering. Application to Advanced Driving Assistance System Validation
  • Etienne Goffinet, Laboratoire Information de Paris-Nord, Université Paris 13, Renault SAS (France)
  • Mustapha Lebbah, Université Paris 13 - LIPN (France )
  • Hanane Azzag, Université Paris 13 - LIPN (France)
  • Loïc Giraldi, CEA (France)
  • Anthony Coutant, HephIA (France)
09:40
Unsupervised Real-time Anomaly Detection for Multivariate Mobile Phone Traffic Series
  • Evelyne Akopyan, University Gustave Eiffel (France)
  • Angelo Furno, University Gustave Eiffel (France)
  • Nour-Eddin El Faouzi, University Gustave Eiffel (France)
  • Eric Gaume, University Gustave Eiffel (France)
10:00
Machine learning and data mining for urban mobility intelligence - poster spotlights
Organized by: Etienne Come, Latifa Oukhellou, Allou Same, Lijun Sun
10:00
In-Station Train Movements Prediction: from Shallow to Deep Multi Scale Models
  • Gianluca Boleto, University of Genoa
  • Luca Oneto, University of Genoa (Italy)
  • Matteo Cardellini, University of Genoa
  • Marco Maratea, University of Genoa (Italy)
  • Mauro Vallati, University of Huddersfield (United Kingdom)
  • Renzo Canepa, Rete Ferroviaria Italiana
  • Davide Anguita, DIBRIS - University of Genova (Italy)
10:01
Deep Neural Networks for Classification of Riding Patterns: with a focus on explainability
  • milad leyli abadi, IRT SystemX (France)
  • abderrahmane boubezoul, Gustave Eiffel University (France)
10:02
A Lightweight Approach for Origin-Destination Matrix Anonymization
  • Benoit Matet, GRETTIA-LICIT/COSYS Université Gustave Eiffel (France)
  • Etienne Come, Univ Gustave Eiffel (France)
  • Angelo Furno, University Gustave Eiffel (France)
  • Loïc Bonnetain, University Gustave Eiffel (France)
  • Latifa Oukhellou, Université Gustave Eiffel (France)
  • Nour-Eddin El Faouzi, University Gustave Eiffel (France)
10:03
Coffee break
 
10:15
Supervised learning
10:15
Supervised learning of convex piecewise linear approximations of optimization problems
  • Laurine Duchesne, University of Liege (Belgium)
  • Quentin Louveaux, University of Liege (Belgium)
  • Louis Wehenkel, University of Liege (Belgium)
10:35
Real-time On-edge Classification: an Application to Domestic Acoustic Event Recognition
  • Lode Vuegen, KU Leuven Campus Geel (Belgium)
  • Peter Karsmakers, KU Leuven Campus Geel (Belgium)
10:55
Functional Gradient Descent for n-Tuple Regression
  • Rafael Katopodis, COPPE, Universidade Federal do Rio de Janeiro (Brazil)
  • Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)
  • Felipe França, Universidade Federal do Rio de Janeiro (Brazil)
11:15
Estimating uncertainty in radiation oncology dose prediction with dropout and bootstrap in U-Net models
  • John Lee, UCLouvain (Belgium)
  • Alyssa Vanginderdeuren, UCLouvain (Belgique)
  • Margerie Huet-Dastarac, UCLouvain (Belgium)
  • Ana Maria Barragan Montero, UCLouvain (Belgium)
11:35
Hierarchical Planning in Multilayered State-Action Networks
  • Matthias Brucklacher, University of Amsterdam (Niederlande)
  • Hanspeter A. Mallot, Eberhard Karls Universität Tübingen (Germany)
  • Tristan Baumann, Eberhard Karls Universität Tübingen (Germany)
11:55
Supervised learning - poster spotlights
11:55
Distribution Preserving Multiple Hypotheses Prediction for Uncertainty Modeling
  • Tobias Leemann, University of Erlangen-Nuremberg (FAU) (Germany)
  • Moritz Sackmann, University of Erlangen Nuremberg (FAU) (Germany)
  • Jörn Thielecke, University of Erlangen Nuremberg (FAU) (Germany)
  • Ulrich Hofmann, Audi AG (Germany)
11:56
Orientation Adaptive Minimal Learning Machine for Directions of Atomic Forces
  • Antti Pihlajamäki, University of Jyväskylä, Department of Physics, Nanoscience Center (Finland)
  • Joakim Linja, University of Jyväskylä Faculty of Information Techonolgy (Finland)
  • Joonas Hämäläinen, University of Jyväskylä, Faculty of Information Technology (Finland)
  • Paavo Nieminen, University of Jyväskylä Faculty of Information Technology (Finland)
  • Sami Malola, University of Jyväskylä, Department of Physics, Nanoscience Center (Finland)
  • Tommi Kärkkäinen, University of Jyvaskyla (Finland)
  • Hannu Häkkinen, University of Jyväskylä, Department of Physics, Department of Chemistry, Nanoscience Center (Finland)
11:57
Estimating Formulas for Model Performance Under Noisy Labels Using Symbolic Regression
  • Fech Scen Khoo, Saarland University, Saarland Informatics Campus (Germany)
  • Dawei Zhu, Saarland University, Saarland Informatics Campus (Germany)
  • Michael A. Hedderich , Saarland University, Saarland Informatics Campus (Germany)
  • Dietrich Klakow, Saarland University, Saarland Informatics Campus (Germany )
11:58
A Multi-ELM Model for Incomplete Data
  • Baichuan Chi, University of Houston (USA)
  • Amaury Lendasse, University of Houston (USA)
  • Edward Ratner, Edammo Inc (USA)
  • Renjie Hu, University of Houston (USA)
11:59
Lunch break
 
13:30
Interpretable Models in Machine Learning and Explainable Artificial Intelligence
Organized by: Sascha Saralajew, Alfredo Vellido, Thomas Villmann, Paulo Lisboa
13:30
The Coming of Age of Interpretable and Explainable Machine Learning Models
  • Paulo Lisboa, Liverpool John Moores University (United Kingdom)
  • Sascha Saralajew, Bosch Center for Artificial Intelligence (Germany)
  • Alfredo Vellido, Universitat Politècnica de Catalunya (UPC BarcelonaTech) (España)
  • Thomas Villmann, University of Applied Sciences Mittweida, Saxon Institute for Computational Intelligence and Machine Learning (Deutschland)
13:50
AGLVQ - Making Generalized Vector Quantization Algorithms Aware of Context
  • Torben Graeber, University of Duisburg Essen - Chair of Mechatronics (Germany)
  • Sebastian Vetter, Porsche AG (Germany)
  • Sascha Saralajew, Bosch Center for Artificial Intelligence (Germany)
  • Michael Unterreiner, Porsche AG
  • Dieter Schramm, University of Duisburg-Essen - Chair of Mechatronics (Germany)
14:10
A Parameterless t-SNE for Faithful Cluster Embeddings from Prototype-based Learning and CONN Similarity
  • Josh Taylor, Rice University (United States)
  • Erzsébet Merényi, Rice University (USA)
14:30
Handling Correlations in Random Forests: which Impacts on Variable Importance and Model Interpretability?
  • Marie Chavent, INRIA Bordeaux Sud-Ouest, CQFD team, France (France)
  • Jérôme Lacaille, Datalab, Safran Aircraft Engines (France)
  • Alex Mourer, SAMM - EA 4543 Université Pantheon Sorbonne, Paris, France Safran Aircraft Engines , Datalab, Villaroche, France INRIA Bordeaux Sud-Ouest, CQFD team, France (France)
  • Madalina Olteanu, CEREMADE, UMR 7534 Université Paris Dauphine PSL - France
14:50
Interpretable Models in Machine Learning and Explainable Artificial Intelligence - poster spotlights
Organized by: Sascha Saralajew, Alfredo Vellido, Thomas Villmann, Paulo Lisboa
14:50
The partial response SVM
  • Bradley Walters, Liverpool John Moores University (United Kingdom)
  • Sandra Ortega-Martorell, Liverpool John Moores University (United Kingdom)
  • Ivan Olier, Liverpool John Moores University (United Kingdom)
  • Paulo Lisboa, Liverpool John Moores University (United Kingdom)
14:51
The LVQ-based Counter Propagation Network -- an Interpretable Information Bottleneck Approach
  • Marika Kaden, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Germany)
  • Ronny Schubert, Hochschule Mittweida (Deutschland)
  • Mehrdad Mohannazadeh Bakhtiari, University of Applied Sciences Mittweida (Deutschland)
  • Lucas Schwarz, University of Applied Sciences Mittweida (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida, Saxon Institute for Computational Intelligence and Machine Learning (Deutschland)
14:52
Geometric Probing of Word Vectors
  • Madina Babazhanova, Nazarbayev University (Kazakhstan)
  • Maxat Tezekbayev, Nazarbayev University (Kazakhstan)
  • Zhenisbek Assylbekov, Nazarbayev University (Kazakhstan)
14:53
Context-specific sampling method for contextual explanations
  • Manik Madhikermi, Umeå University, Department of Computer Science (Sweden)
  • Avleen Malhi, Bournemouth University (England, UK)
  • Kary Främling, Umeå University (Sweden)
14:54
SmoothLRP: Smoothing LRP by Averaging over Stochastic Input Variations
  • Arne Raulf, Ruhr University Bochum (Germany)
  • Sina Däubener, Ruhr University Bochum (please complete)
  • Ben Hack, Ruhr University Bochum (Germany)
  • Axel Mosig, Ruhr University Bochum (Germany)
  • Asja Fischer, Ruhr University Bochum (Germany)
14:55
A Baseline for Shapley Values in MLPs: from Missingness to Neutrality
  • Cosimo Izzo, UCL (Italy)
  • Aldo Lipani, UCL (United Kingdom)
  • Ramin Okhrati, University College London (United Kingdom)
  • Francesca Medda
14:56
Coffee break
 
15:10
Time series and signal processing
15:10
Quantifying Resemblance of Synthetic Medical Time-Series
  • Karan Bhanot, Rensselaer Polytechnic Institute (United States)
  • Saloni Dash, Microsoft Research (India)
  • Joseph Pedersen, Rensselaer Polytechnic Institute (USA)
  • Isabelle Guyon, Université Paris-Saclay (France)
  • Kristin Bennett, Rensselaer Polytechnic Institute (United States)
15:30
Time series and signal processing - poster spotlights
15:30
Differentially Private Time Series Generation
  • Hiba Arnout, TU München/ Siemens AG (Germany)
  • Johanna Bronner, Siemens AG (Germany)
  • Thomas Runkler, Siemens AG/ TU Munich (Germany)
15:31
Fusion of estimations from two modalities using the Viterbi's algorithm: application to fetal heart rate monitoring
  • Rémi Souriau, Univ. Grenoble Alpes, CNRS, Grenoble INP, TIMC, 38000 Grenoble, France (France)
  • Julie Fontecave-Jallon, Univ. Grenoble Alpes, CNRS, Grenoble INP, TIMC, 38000 Grenoble, France (France)
  • Bertrand Rivet, Univ. Grenoble Alpes - CNRS, Grenoble INP, GIPSA-lab, 38000 Grenoble, France (France)
15:32
Convolutional Neural Network Architecture for Classification of Aircraft Engines Flight Time Series
  • Delphine Bay, Safran Aircraft Engines (France)
  • Clémence Bisot, Safran Aircraft Engines (France)
15:33
Multi-perspective embedding for non-metric time series classification
  • Maximilian Münch, University of Applied Sciences Würzburg-Schweinfurt University of Groningen (Germany)
  • Simon Heilig, University of Applied Sciences Würzburg-Schweinfurt (Germany)
  • Frank-Michael Schleif, University of Applied Sciences Würzburg-Schweinfurt (Germany)
15:34
IF: Iterative Fractional Optimization
  • Sarthak Chatterjee, Rensselaer Polytechnic Institute (USA)
  • Subhro Das, IBM Research (USA)
  • Sérgio Pequito, Delft Center for Systems and Control, Delft University of Technology (The Netherlands)
15:36
Classification - poster spotlights
15:36
A Relational Model for One-Shot Classification
  • Arturs Polis, Aalto University, Department of Computer Science (Finland)
  • Alexander Ilin, Aalto University, Despartment of Computer Science (Finland)
15:37
Instance-Based Multi-Label Classification via Multi-Target Distance Regression
  • Joonas Hämäläinen, University of Jyväskylä, Faculty of Information Technology (Finland)
  • Paavo Nieminen, University of Jyväskylä Faculty of Information Technology (Finland)
  • Tommi Kärkkäinen, University of Jyvaskyla, Faculty of Information Technology (Finland)
15:38
A bag of nodes primer on weightless graph classification
  • Raul Barbosa, Federal University of Rio de Janeiro (Brazil)
  • Diego Carvalho, Cefet/RJ (Brazil)
  • Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)
  • Felipe França, Universidade Federal do Rio de Janeiro (Brazil)
15:39
Gradient representations in ReLU networks as similarity functions
  • Bálint Daróczy, Université catholique de Louvain (Belgium)
  • Dániel Rácz, Institute for Computer Science and Control (SZTAKI) (Hungary)
15:40
Poster exhibition
 
17:30
End of conference