4 papers
The Effect of Data Poisoning on Counterfactual Explanations
André Artelt, Shubham Sharma, Freddy Lecué +1
Counterfactual explanations are a widely used approach for examining the predictions of black-box systems. They can offer the opportunity for computational recourse by suggesting a…
Interpretable Event Diagnosis in Water Distribution Networks
André Artelt, Stelios G. Vrachimis, Demetrios G. Eliades +3
The increasing penetration of information and communication technologies in the design, monitoring, and control of water systems enables the use of algorithms for detecting and ide…
Towards Understanding the Influence of Training Samples on Explanations
André Artelt, Barbara Hammer
Explainable AI (XAI) is widely used to analyze AI systems' decision-making, such as providing counterfactual explanations for recourse. When unexpected explanations occur, users ma…
Scalable and Robust Physics-Informed Graph Neural Networks for Water Distribution Systems
Inaam Ashraf, André Artelt, Barbara Hammer
Water distribution systems (WDSs) are an important part of critical infrastructure becoming increasingly significant in the face of climate change and urban population growth. We p…