Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Gjergji Kasneci

Gjergji Kasneci

Standardized Evaluation of Machine Learning Methods for Evolving Data Streams


Apr 28, 2022
Johannes Haug, Effi Tramountani, Gjergji Kasneci

Figure 1 for Standardized Evaluation of Machine Learning Methods for Evolving Data Streams
Figure 2 for Standardized Evaluation of Machine Learning Methods for Evolving Data Streams
Figure 3 for Standardized Evaluation of Machine Learning Methods for Evolving Data Streams
Figure 4 for Standardized Evaluation of Machine Learning Methods for Evolving Data Streams

  Access Paper or Ask Questions

Dynamic Model Tree for Interpretable Data Stream Learning


Mar 30, 2022
Johannes Haug, Klaus Broelemann, Gjergji Kasneci

Figure 1 for Dynamic Model Tree for Interpretable Data Stream Learning
Figure 2 for Dynamic Model Tree for Interpretable Data Stream Learning
Figure 3 for Dynamic Model Tree for Interpretable Data Stream Learning
Figure 4 for Dynamic Model Tree for Interpretable Data Stream Learning
* To be published in the proceedings of the 38th IEEE International Conference on Data Engineering (ICDE 2022) 
  Access Paper or Ask Questions

Algorithmic Recourse in the Face of Noisy Human Responses


Mar 13, 2022
Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel, Gjergji Kasneci, Himabindu Lakkaraju

Figure 1 for Algorithmic Recourse in the Face of Noisy Human Responses
Figure 2 for Algorithmic Recourse in the Face of Noisy Human Responses
Figure 3 for Algorithmic Recourse in the Face of Noisy Human Responses
Figure 4 for Algorithmic Recourse in the Face of Noisy Human Responses

  Access Paper or Ask Questions

Gaussian Graphical Models as an Ensemble Method for Distributed Gaussian Processes


Feb 07, 2022
Hamed Jalali, Gjergji Kasneci

* OPT2021: 13th Annual Workshop on Optimization for Machine Learning 
  Access Paper or Ask Questions

Evaluating Feature Attribution: An Information-Theoretic Perspective


Feb 01, 2022
Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci

* 9 pages, 8 figures. The first two authors contributed equally 
  Access Paper or Ask Questions

A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines


Nov 14, 2021
Vadim Borisov, Johannes Meier, Johan van den Heuvel, Hamed Jalali, Gjergji Kasneci

Figure 1 for A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
Figure 2 for A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
Figure 3 for A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
Figure 4 for A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines

  Access Paper or Ask Questions

Deep Neural Networks and Tabular Data: A Survey


Oct 05, 2021
Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, Gjergji Kasneci

Figure 1 for Deep Neural Networks and Tabular Data: A Survey
Figure 2 for Deep Neural Networks and Tabular Data: A Survey
Figure 3 for Deep Neural Networks and Tabular Data: A Survey
Figure 4 for Deep Neural Networks and Tabular Data: A Survey

  Access Paper or Ask Questions

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms


Aug 02, 2021
Martin Pawelczyk, Sascha Bielawski, Johannes van den Heuvel, Tobias Richter, Gjergji Kasneci

Figure 1 for CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Figure 2 for CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Figure 3 for CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Figure 4 for CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
* Accepted to NeurIPS Benchmark & Data Set Track 
  Access Paper or Ask Questions

Gaussian Experts Selection using Graphical Models


Feb 04, 2021
Hamed Jalali, Martin Pawelczyk, Gjergji Kasneci

Figure 1 for Gaussian Experts Selection using Graphical Models
Figure 2 for Gaussian Experts Selection using Graphical Models
Figure 3 for Gaussian Experts Selection using Graphical Models
Figure 4 for Gaussian Experts Selection using Graphical Models

  Access Paper or Ask Questions

TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types


Feb 03, 2021
Wolfgang Fuhl, Gjergji Kasneci, Enkelejda Kasneci

Figure 1 for TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types
Figure 2 for TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types
Figure 3 for TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types
Figure 4 for TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types

  Access Paper or Ask Questions

On Baselines for Local Feature Attributions


Jan 04, 2021
Johannes Haug, Stefan Zürn, Peter El-Jiz, Gjergji Kasneci

Figure 1 for On Baselines for Local Feature Attributions
Figure 2 for On Baselines for Local Feature Attributions
Figure 3 for On Baselines for Local Feature Attributions
Figure 4 for On Baselines for Local Feature Attributions
* Accepted at the AAAI-21 Workshop on Explainable Agency in AI 
  Access Paper or Ask Questions

Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots


Oct 29, 2020
Nikolaos Nikolaou, Ingo P. Waldmann, Angelos Tsiaras, Mario Morvan, Billy Edwards, Kai Hou Yip, Giovanna Tinetti, Subhajit Sarkar, James M. Dawson, Vadim Borisov, Gjergji Kasneci, Matej Petkovic, Tomaz Stepisnik, Tarek Al-Ubaidi, Rachel Louise Bailey, Michael Granitzer, Sahib Julka, Roman Kern, Patrick Ofner, Stefan Wagner, Lukas Heppe, Mirko Bunse, Katharina Morik

Figure 1 for Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots
Figure 2 for Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots
Figure 3 for Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots
Figure 4 for Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots
* 20 pages, 7 figures, 2 tables, Submitted to The Astrophysics Journal (ApJ) 
  Access Paper or Ask Questions

Learning Parameter Distributions to Detect Concept Drift in Data Streams


Oct 19, 2020
Johannes Haug, Gjergji Kasneci

Figure 1 for Learning Parameter Distributions to Detect Concept Drift in Data Streams
Figure 2 for Learning Parameter Distributions to Detect Concept Drift in Data Streams
Figure 3 for Learning Parameter Distributions to Detect Concept Drift in Data Streams
Figure 4 for Learning Parameter Distributions to Detect Concept Drift in Data Streams
* To be published in the proceedings of the 25th International Conference on Pattern Recognition (ICPR 2020) 
  Access Paper or Ask Questions

Aggregating Dependent Gaussian Experts in Local Approximation


Oct 17, 2020
Hamed Jalali, Gjergji Kasneci

Figure 1 for Aggregating Dependent Gaussian Experts in Local Approximation
Figure 2 for Aggregating Dependent Gaussian Experts in Local Approximation
Figure 3 for Aggregating Dependent Gaussian Experts in Local Approximation
Figure 4 for Aggregating Dependent Gaussian Experts in Local Approximation
* 8 pages 
  Access Paper or Ask Questions

On Counterfactual Explanations under Predictive Multiplicity


Jun 23, 2020
Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci

Figure 1 for On Counterfactual Explanations under Predictive Multiplicity
Figure 2 for On Counterfactual Explanations under Predictive Multiplicity
Figure 3 for On Counterfactual Explanations under Predictive Multiplicity
Figure 4 for On Counterfactual Explanations under Predictive Multiplicity
* Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), PMLR volume 124, 2020 
  Access Paper or Ask Questions

Leveraging Model Inherent Variable Importance for Stable Online Feature Selection


Jun 18, 2020
Johannes Haug, Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci

Figure 1 for Leveraging Model Inherent Variable Importance for Stable Online Feature Selection
Figure 2 for Leveraging Model Inherent Variable Importance for Stable Online Feature Selection
Figure 3 for Leveraging Model Inherent Variable Importance for Stable Online Feature Selection
Figure 4 for Leveraging Model Inherent Variable Importance for Stable Online Feature Selection
* To be published in the Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2020) 
  Access Paper or Ask Questions

Towards User Empowerment


Oct 21, 2019
Martin Pawelczyk, Johannes Haug, Klaus Broelemann, Gjergji Kasneci

Figure 1 for Towards User Empowerment
Figure 2 for Towards User Empowerment
Figure 3 for Towards User Empowerment
Figure 4 for Towards User Empowerment

  Access Paper or Ask Questions

Training decision trees as replacement for convolution layers


Jun 05, 2019
Wolfgang Fuhl, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci

Figure 1 for Training decision trees as replacement for convolution layers
Figure 2 for Training decision trees as replacement for convolution layers
Figure 3 for Training decision trees as replacement for convolution layers
Figure 4 for Training decision trees as replacement for convolution layers

  Access Paper or Ask Questions

Validation loss for landmark detection


Jan 30, 2019
Wolfgang Fuhl, Thomas Kübler, Rene Alexander Lotz, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci

Figure 1 for Validation loss for landmark detection
Figure 2 for Validation loss for landmark detection
Figure 3 for Validation loss for landmark detection
Figure 4 for Validation loss for landmark detection
* 11 pages with references 
  Access Paper or Ask Questions

A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees


Sep 25, 2018
Klaus Broelemann, Gjergji Kasneci

Figure 1 for A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees
Figure 2 for A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees
Figure 3 for A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees
Figure 4 for A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees

  Access Paper or Ask Questions

Combining Restricted Boltzmann Machines with Neural Networks for Latent Truth Discovery


Jul 27, 2018
Klaus Broelemann, Gjergji Kasneci

Figure 1 for Combining Restricted Boltzmann Machines with Neural Networks for Latent Truth Discovery
Figure 2 for Combining Restricted Boltzmann Machines with Neural Networks for Latent Truth Discovery
Figure 3 for Combining Restricted Boltzmann Machines with Neural Networks for Latent Truth Discovery

  Access Paper or Ask Questions

Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery


Dec 31, 2017
Klaus Broelemann, Thomas Gottron, Gjergji Kasneci

Figure 1 for Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery
Figure 2 for Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery
Figure 3 for Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery
Figure 4 for Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery

  Access Paper or Ask Questions

PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection


Oct 30, 2017
Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci

Figure 1 for PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
Figure 2 for PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
Figure 3 for PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
Figure 4 for PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
* Pupil detection, pupil center estimation, image processing, CNN. arXiv admin note: substantial text overlap with arXiv:1601.04902 
  Access Paper or Ask Questions

PupilNet: Convolutional Neural Networks for Robust Pupil Detection


Jan 19, 2016
Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, Enkelejda Kasneci

Figure 1 for PupilNet: Convolutional Neural Networks for Robust Pupil Detection
Figure 2 for PupilNet: Convolutional Neural Networks for Robust Pupil Detection
Figure 3 for PupilNet: Convolutional Neural Networks for Robust Pupil Detection
Figure 4 for PupilNet: Convolutional Neural Networks for Robust Pupil Detection
* 9 pages, 11 figures 
  Access Paper or Ask Questions

SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases


Jul 19, 2012
Simon Lacoste-Julien, Konstantina Palla, Alex Davies, Gjergji Kasneci, Thore Graepel, Zoubin Ghahramani

Figure 1 for SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases
Figure 2 for SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases
Figure 3 for SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases
Figure 4 for SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases
* 10 pages + 2 pages appendix; 5 figures -- initial preprint 
  Access Paper or Ask Questions