Gjergji Kasneci

research

∙ 08/04/2023

Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes

We introduce a novel semi-supervised Graph Counterfactual Explainer (GCE...

0 Bardh Prenkaj, et al. ∙

research

∙ 07/25/2023

Counterfactual Explanation via Search in Gaussian Mixture Distributed Latent Space

Counterfactual Explanations (CEs) are an important tool in Algorithmic R...

0 Xuan Zhao, et al. ∙

research

∙ 06/12/2023

Gaussian Membership Inference Privacy

We propose a new privacy notion called f-Membership Inference Privacy (f...

0 Tobias Leemann, et al. ∙

research

∙ 03/14/2023

Explanation Shift: Investigating Interactions between Models and Shifting Data Distributions

As input data distributions evolve, the predictive performance of machin...

0 Carlos Mougan, et al. ∙

research

∙ 11/17/2022

Expert Selection in Distributed Gaussian Processes: A Multi-label Classification Approach

By distributing the training process, local approximation reduces the co...

0 Hamed Jalali, et al. ∙

research

∙ 11/03/2022

Decomposing Counterfactual Explanations for Consequential Decision Making

The goal of algorithmic recourse is to reverse unfavorable decisions (e....

0 Martin Pawelczyk, et al. ∙

research

∙ 10/25/2022

I Prefer not to Say: Operationalizing Fair and User-guided Data Minimization

To grant users greater authority over their personal data, policymakers ...

0 Tobias Leemann, et al. ∙

research

∙ 10/22/2022

Explanation Shift: Detecting distribution shifts on tabular data via the explanation space

As input data distributions evolve, the predictive performance of machin...

0 Carlos Mougan, et al. ∙

research

∙ 10/20/2022

Towards Human-centered Explainable AI: User Studies for Model Explanations

Explainable AI (XAI) is widely viewed as a sine qua non for ever-expandi...

17 Yao Rong, et al. ∙

research

∙ 09/06/2022

Change Detection for Local Explainability in Evolving Data Streams

As complex machine learning models are increasingly used in sensitive ap...

0 Johannes Haug, et al. ∙

research

∙ 08/30/2022

On the Trade-Off between Actionable Explanations and the Right to be Forgotten

As machine learning (ML) models are increasingly being deployed in high-...

8 Martin Pawelczyk, et al. ∙

research

∙ 06/28/2022

Disentangling Embedding Spaces with Minimal Distributional Assumptions

Interest in understanding and factorizing learned embedding spaces is gr...

6 Tobias Leemann, et al. ∙

research

∙ 06/08/2022

Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation

With increasing digitalization, Artificial Intelligence (AI) is becoming...

0 Alejandra Bringas Colmenarejo, et al. ∙

research

∙ 04/28/2022

Standardized Evaluation of Machine Learning Methods for Evolving Data Streams

Due to the unspecified and dynamic nature of data streams, online machin...

0 Johannes Haug, et al. ∙

research

∙ 03/30/2022

Dynamic Model Tree for Interpretable Data Stream Learning

Data streams are ubiquitous in modern business and society. In practice,...

0 Johannes Haug, et al. ∙

research

∙ 03/13/2022

Algorithmic Recourse in the Face of Noisy Human Responses

As machine learning (ML) models are increasingly being deployed in high-...

13 Martin Pawelczyk, et al. ∙

research

∙ 02/07/2022

Gaussian Graphical Models as an Ensemble Method for Distributed Gaussian Processes

Distributed Gaussian process (DGP) is a popular approach to scale GP to ...

0 Hamed Jalali, et al. ∙

research

∙ 08/02/2021

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

Counterfactual explanations provide means for prescriptive model explana...

203 Martin Pawelczyk, et al. ∙

research

∙ 02/03/2021

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

We present TEyeD, the world's largest unified public data set of eye ima...

8 Wolfgang Fuhl, et al. ∙

research

∙ 02/02/2021

Gaussian Experts Selection using Graphical Models

Local approximations are popular methods to scale Gaussian processes (GP...

8 Hamed Jalali, et al. ∙

research

∙ 01/04/2021

On Baselines for Local Feature Attributions

High-performing predictive models, such as neural nets, usually operate ...

0 Johannes Haug, et al. ∙

research

∙ 10/29/2020

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

The last decade has witnessed a rapid growth of the field of exoplanet d...

9 Nikolaos Nikolaou, et al. ∙

research

∙ 10/19/2020

Learning Parameter Distributions to Detect Concept Drift in Data Streams

Data distributions in streaming environments are usually not stationary....

0 Johannes Haug, et al. ∙

research

∙ 10/17/2020

Aggregating Dependent Gaussian Experts in Local Approximation

Distributed Gaussian processes (DGPs) are prominent local approximation ...

0 Hamed Jalali, et al. ∙

research

∙ 06/23/2020

On Counterfactual Explanations under Predictive Multiplicity

Counterfactual explanations are usually obtained by identifying the smal...

0 Martin Pawelczyk, et al. ∙

research

∙ 06/18/2020

Leveraging Model Inherent Variable Importance for Stable Online Feature Selection

Feature selection can be a crucial factor in obtaining robust and accura...

0 Johannes Haug, et al. ∙

research

∙ 01/14/2020

Bias in Data-driven AI Systems – An Introductory Survey

AI-based systems are widely employed nowadays to make decisions that hav...

0 Eirini Ntoutsi, et al. ∙

research

∙ 10/21/2019

Towards User Empowerment

Counterfactual explanations can be obtained by identifying the smallest ...

0 Martin Pawelczyk, et al. ∙

research

∙ 05/24/2019

Training decision trees as replacement for convolution layers

We present an alternative layer to convolution layers in convolutional n...

0 Wolfgang Fuhl, et al. ∙

research

∙ 01/29/2019

Validation loss for landmark detection

We present a new loss function for the validation of image landmarks det...

12 Wolfgang Fuhl, et al. ∙

research

∙ 09/25/2018

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

Machine learning algorithms aim at minimizing the number of false decisi...

0 Klaus Broelemann, et al. ∙

research

∙ 07/27/2018

Combining Restricted Boltzmann Machines with Neural Networks for Latent Truth Discovery

Latent truth discovery, LTD for short, refers to the problem of aggregat...

0 Klaus Broelemann, et al. ∙

research

∙ 12/31/2017

Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery

We address the problem of latent truth discovery, LTD for short, where t...

0 Klaus Broelemann, et al. ∙

research

∙ 10/30/2017

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

Real-time, accurate, and robust pupil detection is an essential prerequi...

0 Wolfgang Fuhl, et al. ∙

research

∙ 01/19/2016

PupilNet: Convolutional Neural Networks for Robust Pupil Detection

Real-time, accurate, and robust pupil detection is an essential prerequi...

0 Wolfgang Fuhl, et al. ∙

research

∙ 07/19/2012

SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases

The Internet has enabled the creation of a growing number of large-scale...

0 Simon Lacoste-Julien, et al. ∙

Gjergji Kasneci

Featured Co-authors