53 citations · 173 across the 27 of their papers we have counts for
27 papers
Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers
Philip Kenneweg, Alexander Schulz, Sarah Schröder +1
Pretraining language models on large text corpora is a common practice in natural language processing. Fine-tuning of these models is then performed to achieve the best results on…
Debiasing Sentence Embedders through Contrastive Word Pairs
Philip Kenneweg, Sarah Schröder, Alexander Schulz +1
Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately…
iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios
Maximilian Muschalik, Fabian Fumagalli, Rohit Jagtani +2
Post-hoc explanation techniques such as the well-established partial dependence plot (PDP), which investigates feature dependencies, are used in explainable artificial intelligence…
For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI
Ulrike Kuhl, André Artelt, Barbara Hammer
Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model's output.…
Adversarial Attacks on Leakage Detectors in Water Distribution Networks
Paul Stahlhofen, André Artelt, Luca Hermes +1
Many Machine Learning models are vulnerable to adversarial attacks: There exist methodologies that add a small (imperceptible) perturbation to an input such that the model comes up…
Model Based Explanations of Concept Drift
Fabian Hinder, Valerie Vaquet, Johannes Brinkrolf +1
The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models can become i…
iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams
Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer +1
Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. Ho…
SHAP-IQ: Unified Approximation of any-order Shapley Interactions
Fabian Fumagalli, Maximilian Muschalik, Patrick Kolpaczki +2
Predominately in explainable artificial intelligence (XAI) research, the Shapley value (SV) is applied to determine feature attributions for any black box model. Shapley interactio…
Combining self-labeling and demand based active learning for non-stationary data streams
Valerie Vaquet, Fabian Hinder, Johannes Brinkrolf +1
Learning from non-stationary data streams is a research direction that gains increasing interest as more data in form of streams becomes available, for example from social media, s…
On the Change of Decision Boundaries and Loss in Learning with Concept Drift
Fabian Hinder, Valerie Vaquet, Johannes Brinkrolf +1
The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models may become i…
Explainable Artificial Intelligence for Improved Modeling of Processes
Riza Velioglu, Jan Philip Göpfert, André Artelt +1
In modern business processes, the amount of data collected has increased substantially in recent years. Because this data can potentially yield valuable insights, automated knowled…
"Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanations
André Artelt, Barbara Hammer
Counterfactual explanations are a popular type of explanation for making the outcomes of a decision making system transparent to the user. Counterfactual explanations tell the user…
Spatial Graph Convolution Neural Networks for Water Distribution Systems
Inaam Ashraf, Luca Hermes, André Artelt +1
We investigate the task of missing value estimation in graphs as given by water distribution systems (WDS) based on sparse signals as a representative machine learning challenge in…
Unsupervised Unlearning of Concept Drift with Autoencoders
André Artelt, Kleanthis Malialis, Christos Panayiotou +2
Concept drift refers to a change in the data distribution affecting the data stream of future samples. Consequently, learning models operating on the data stream might become obsol…
Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams
Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier +1
Explainable Artificial Intelligence (XAI) has mainly focused on static learning scenarios so far. We are interested in dynamic scenarios where data is sampled progressively, and le…
"Even if ..." -- Diverse Semifactual Explanations of Reject
André Artelt, Barbara Hammer
Machine learning based decision making systems applied in safety critical areas require reliable high certainty predictions. For this purpose, the system can be extended by an reje…
One Explanation to Rule them All -- Ensemble Consistent Explanations
André Artelt, Stelios Vrachimis, Demetrios Eliades +2
Transparency is a major requirement of modern AI based decision making systems deployed in real world. A popular approach for achieving transparency is by means of explanations. A…
Model Agnostic Local Explanations of Reject
André Artelt, Roel Visser, Barbara Hammer
The application of machine learning based decision making systems in safety critical areas requires reliable high certainty predictions. Reject options are a common way of ensuring…
Precise Change Point Detection using Spectral Drift Detection
Fabian Hinder, André Artelt, Valerie Vaquet +1
The notion of concept drift refers to the phenomenon that the data generating distribution changes over time; as a consequence machine learning models may become inaccurate and nee…
Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting
Ulrike Kuhl, André Artelt, Barbara Hammer
Counterfactual explanations (CFEs) highlight what changes to a model's input would have changed its prediction in a particular way. CFEs have gained considerable traction as a psyc…
Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learning
Ulrike Kuhl, André Artelt, Barbara Hammer
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field o…
SAM-kNN Regressor for Online Learning in Water Distribution Networks
Jonathan Jakob, André Artelt, Martina Hasenjäger +1
Water distribution networks are a key component of modern infrastructure for housing and industry. They transport and distribute water via widely branched networks from sources to…
Stream-based Active Learning with Verification Latency in Non-stationary Environments
Andrea Castellani, Sebastian Schmitt, Barbara Hammer
Data stream classification is an important problem in the field of machine learning. Due to the non-stationary nature of the data where the underlying distribution changes over tim…
The SAME score: Improved cosine based bias score for word embeddings
Sarah Schröder, Alexander Schulz, Barbara Hammer
With the enourmous popularity of large language models, many researchers have raised ethical concerns regarding social biases incorporated in such models. Several methods to measur…