Search Results for author:
Found 90 papers, 53 papers with code
FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when exposed to non-model-worn apparel and close-up shots.
Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers
We combine the learning rate distributions thus found and show that they generalize to better performance with respect to the problem of catastrophic forgetting.
Debiasing Sentence Embedders through Contrastive Word Pairs
It is problematic that most debiasing approaches are directly transferred from word embeddings, therefore these approaches fail to take into account the nonlinear nature of sentence embedders and the embeddings they produce.
Neural Architecture Search for Sentence Classification with BERT
Pre training of language models on large text corpora is common practice in Natural Language Processing.
Faster Convergence for Transformer Fine-tuning with Line Search Methods
Recent works have shown that line search methods greatly increase performance of traditional stochastic gradient descent methods on a variety of datasets and architectures [1], [2].
Improving Line Search Methods for Large Scale Neural Network Training
In recent studies, line search methods have shown significant improvements in the performance of traditional stochastic gradient descent techniques, eliminating the need for a specific learning rate schedule.
Physics-Informed Graph Neural Networks for Water Distribution Systems
In this realm, we propose a novel and efficient machine learning emulator, more precisely, a physics-informed deep learning (DL) model, for hydraulic state estimation in WDS.
Targeted Visualization of the Backbone of Encoder LLMs
Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP).
Retrieval Augmented Generation Systems: Automatic Dataset Creation, Evaluation and Boolean Agent Setup
We use a dataset created this way for the development and evaluation of a boolean agent RAG setup: A system in which a LLM can decide whether to query a vector database or not, thus saving tokens on questions that can be answered with internal knowledge.
The Effect of Data Poisoning on Counterfactual Explanations
Counterfactual explanations provide a popular method for analyzing the predictions of black-box systems, and they can offer the opportunity for computational recourse by suggesting actionable changes on how to change the input to obtain a different (i. e. more favorable) system output.
Semantic Properties of cosine based bias scores for word embeddings
Furthermore, we formally analyze cosine based scores from the literature with regard to these requirements.
Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles
While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Investigating the Suitability of Concept Drift Detection for Detecting Leakages in Water Distribution Networks
In this work, we explore the potential of model-loss-based and distribution-based drift detection methods to tackle leakage detection.
A Remark on Concept Drift for Dependent Data
Concept drift, i. e., the change of the data generating distribution, can render machine learning models inaccurate.
Localizing Anomalies in Critical Infrastructure using Model-Based Drift Explanations
Facing climate change, the already limited availability of drinking water will decrease in the future rendering drinking water an increasingly scarce resource.
One or Two Things We know about Concept Drift -- A Survey on Monitoring Evolving Environments
In addition to providing a systematic literature review, this work provides precise mathematical definitions of the considered problems and contains standardized experiments on parametric artificial datasets allowing for a direct comparison of different strategies for detection and localization.
Fairness in KI-Systemen
We explain the main fairness definitions and strategies for achieving fairness using concrete examples and place fairness research in the European context.
iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios
Post-hoc explanation techniques such as the well-established partial dependence plot (PDP), which investigates feature dependencies, are used in explainable artificial intelligence (XAI) to understand black-box machine learning models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI
However, potential benefits and drawbacks of the directionality of CFEs for user behavior in xAI remain unclear.
Adversarial Attacks on Leakage Detectors in Water Distribution Networks
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 with a wrong prediction.
Model Based Explanations of Concept Drift
To do so, we propose a methodology to reduce the explanation of concept drift to an explanation of models that are trained in a suitable way extracting relevant information regarding the drift.
iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams
Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
Combining self-labeling and demand based active learning for non-stationary data streams
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, smartphones, or industrial process monitoring.
On the Change of Decision Boundaries and Loss in Learning with Concept Drift
More precisely, we relate a change of the ITTE to the presence of real drift, i. e., a changed posterior, and to a change of the training result under the assumption of optimality.
Explainable Artificial Intelligence for Improved Modeling of Processes
On the other hand, Machine Learning (ML) benefits from the vast amount of data available and can deal with high-dimensional sources, yet it has rarely been applied to being used in processes.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
"Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanations
Counterfactual explanations are a popular type of explanation for making the outcomes of a decision making system transparent to the user.
Unsupervised Unlearning of Concept Drift with Autoencoders
Consequently, learning models operating on the data stream might become obsolete, and need costly and difficult adjustments such as retraining or adaptation.
Novel transfer learning schemes based on Siamese networks and synthetic data
We make the data sets available at https://pub. uni-bielefeld. de/record/2960030.
Spatial Graph Convolution Neural Networks for Water Distribution Systems
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 the domain of critical infrastructure.
Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams
Explainable Artificial Intelligence (XAI) has mainly focused on static learning scenarios so far.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
"Even if ..." -- Diverse Semifactual Explanations of Reject
In this work, we propose to explain rejects by semifactual explanations, an instance of example-based explanation methods, which them self have not been widely considered in the XAI community yet.
"Why Here and Not There?" -- Diverse Contrasting Explanations of Dimensionality Reduction
Dimensionality reduction is a popular preprocessing and a widely used tool in data mining.
One Explanation to Rule them All -- Ensemble Consistent Explanations
Transparency is a major requirement of modern AI based decision making systems deployed in real world.
Model Agnostic Local Explanations of Reject
The application of machine learning based decision making systems in safety critical areas requires reliable high certainty predictions.
Precise Change Point Detection using Spectral Drift Detection
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 need adjustment.
Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting
Following the view of psychological plausibility as comparative similarity, this may be explained by the fact that users in the closest condition experience their CFEs as more psychologically plausible than the computationally plausible counterpart.
Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learning
Thus, to advance the field of XAI, we introduce the Alien Zoo, an engaging, web-based and game-inspired experimental framework.
Stream-based Active Learning with Verification Latency in Non-stationary Environments
Furthermore, we propose a drift-dependent dynamic budget strategy, which uses a variable distribution of the labelling budget over time, after a detected drift.
SAM-kNN Regressor for Online Learning in Water Distribution Networks
In this work, we propose an adaption of the incremental SAM-kNN classifier for regression to build a residual based anomaly detection system for water distribution networks that is able to adapt to any kind of change.
The SAME score: Improved cosine based bias score for word embeddings
Furthermore, we thoroughly investigate the existing cosine-based scores and their limitations in order to show why these scores fail to report biases in some situations.
BERT WEAVER: Using WEight AVERaging to enable lifelong learning for transformer-based models in biomedical semantic search engines
Recent developments in transfer learning have boosted the advancements in natural language processing tasks.
Suitability of Different Metric Choices for Concept Drift Detection
In this paper, we analyze structural properties of the drift induced signals in the context of different metrics.
Explaining Reject Options of Learning Vector Quantization Classifiers
While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty would be possible.
A Graph-based U-Net Model for Predicting Traffic in unseen Cities
Accurate traffic prediction is a key ingredient to enable traffic management like rerouting cars to reduce road congestion or regulating traffic via dynamic speed limits to maintain a steady flow.
Evaluating Metrics for Bias in Word Embeddings
However, lately some works have raised doubts about these metrics showing that even though such metrics report low biases, other tests still show biases.
Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting
Prediction of movements is essential for successful cooperation with intelligent systems.
Task-Sensitive Concept Drift Detector with Constraint Embedding
In the proposed framework, the actual method to detect a change in the statistics of incoming data samples can be chosen freely.
Single-Step Adversarial Training for Semantic Segmentation
Finding such a step size, without increasing the computational effort of single-step adversarial training, is still an open challenge.
Convex optimization for actionable \& plausible counterfactual explanations
Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world.
Reservoir Stack Machines
In this paper, we introduce the reservoir stack machine, a model which can provably recognize all deterministic context-free languages and circumvents the training problem by training only the output layer of a recurrent net and employing auxiliary information during training about the desired interaction with a stack.
Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise
However, sensor failures result in mislabeled training data samples which are hard to detect and remove from the dataset.
Contrastive Explanations for Explaining Model Adaptations
We also propose a method for automatically finding regions in data space that are affected by a given model adaptation and thus should be explained.
Evaluating Robustness of Counterfactual Explanations
Counterfactual explanations explain a behavior to the user by proposing actions -- as changes to the input -- that would cause a different (specified) behavior of the system.
Intuitiveness in Active Teaching
After developing a theoretical framework of intuitiveness as a property of algorithms, we introduce an active teaching paradigm involving a prototypical two-dimensional spatial learning task as a method to judge the efficacy of human-machine interactions.
Analysis of Drifting Features
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time.
Interpretable Locally Adaptive Nearest Neighbors
When training automated systems, it has been shown to be beneficial to adapt the representation of data by learning a problem-specific metric.
Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation
Motivation: Innovative microfluidic systems carry the promise to greatly facilitate spatio-temporal analysis of single cells under well-defined environmental conditions, allowing novel insights into population heterogeneity and opening new opportunities for fundamental and applied biotechnology.
Efficient computation of contrastive explanations
With the increasing deployment of machine learning systems in practice, transparency and explainability have become serious issues.
Reservoir Memory Machines as Neural Computers
Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal.
Counterfactual Explanations of Concept Drift
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment.
Supervised Learning in the Presence of Concept Drift: A modelling framework
We present a modelling framework for the investigation of supervised learning in non-stationary environments.
Sequential Feature Classification in the Context of Redundancies
The problem of all-relevant feature selection is concerned with finding a relevant feature set with preserved redundancies.
Convex Density Constraints for Computing Plausible Counterfactual Explanations
The increasing deployment of machine learning as well as legal regulations such as EU's GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models.
Feature Relevance Determination for Ordinal Regression in the Context of Feature Redundancies and Privileged Information
In this contribution, we focus on feature selection paradigms, which enable us to uncover relevant factors of a given regularity based on a sparse model.
A probability theoretic approach to drifting data in continuous time domains
The notion of drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time.
On the computation of counterfactual explanations -- A survey
Due to the increasing use of machine learning in practice it becomes more and more important to be able to explain the prediction and behavior of machine learning models.
Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation
Convolutional neural networks (CNNs) are deep learning frameworks which are well-known for their notable performance in classification tasks.
Interpretable Multiple-Kernel Prototype Learning for Discriminative Representation and Feature Selection
In this paper, we propose a novel interpretable multiple-kernel prototype learning (IMKPL) to construct highly interpretable prototypes in the feature space, which are also efficient for the discriminative representation of the data.
Recovering Localized Adversarial Attacks
In this contribution, we focus on the capabilities of explainers for convolutional deep neural networks in an extreme situation: a setting in which humans and networks fundamentally disagree.
DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction
So far, most methods in the literature investigate the decision of the model for a single given input datum.
Interpretable Discriminative Dimensionality Reduction and Feature Selection on the Manifold
In this research, we propose the interpretable kernel DR algorithm (I-KDR) as a new algorithm which maps the data from the feature space to a lower dimensional space where the classes are more condensed with less overlapping.
Efficient computation of counterfactual explanations of LVQ models
The increasing use of machine learning in practice and legal regulations like EU's GDPR cause the necessity to be able to explain the prediction and behavior of machine learning models.
Adversarial Robustness Curves
The existence of adversarial examples has led to considerable uncertainty regarding the trust one can justifiably put in predictions produced by automated systems.
Prototype-based classifiers in the presence of concept drift: A modelling framework
We present a modelling framework for the investigation of prototype-based classifiers in non-stationary environments.
Confident Kernel Sparse Coding and Dictionary Learning
In this work, we propose a novel confident K-SRC and dictionary learning algorithm (CKSC) which focuses on the discriminative reconstruction of the data based on its representation in the kernel space.
Non-Negative Local Sparse Coding for Subspace Clustering
The NLSSC algorithm is also formulated in the kernel-based framework (NLKSSC) which can represent the nonlinear structure of data.
Non-Negative Kernel Sparse Coding for the Classification of Motion Data
We are interested in the decomposition of motion data into a sparse linear combination of base functions which enable efficient data processing.
Large-Margin Multiple Kernel Learning for Discriminative Features Selection and Representation Learning
Multiple kernel learning (MKL) algorithms combine different base kernels to obtain a more efficient representation in the feature space.
Multiple-Kernel Dictionary Learning for Reconstruction and Clustering of Unseen Multivariate Time-series
Furthermore, we obtain sparse encodings for unseen classes based on the learned MKD attributes, and upon which we propose a simple but effective incremental clustering algorithm to categorize the unseen MTS classes in an unsupervised way.
FRI -- Feature Relevance Intervals for Interpretable and Interactive Data Exploration
Most existing feature selection methods are insufficient for analytic purposes as soon as high dimensional data or redundant sensor signals are dealt with since features can be selected due to spurious effects or correlations rather than causal effects.
Adversarial attacks hidden in plain sight
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue.
Feature Relevance Bounds for Ordinal Regression
The increasing occurrence of ordinal data, mainly sociodemographic, led to a renewed research interest in ordinal regression, i. e. the prediction of ordered classes.
Progressive Data Science: Potential and Challenges
We discuss these challenges and outline first steps towards progressiveness, which, we argue, will ultimately help to significantly speed-up the overall data science process.
Tree Edit Distance Learning via Adaptive Symbol Embeddings
Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart.
Expectation maximization transfer learning and its application for bionic hand prostheses
Machine learning models in practical settings are typically confronted with changes to the distribution of the incoming data.
The Continuous Hint Factory - Providing Hints in Vast and Sparsely Populated Edit Distance Spaces
In particular, we extend the Hint Factory by considering data of past students in all states which are similar to the student's current state and creating hints approximating the weighted average of all these reference states.
Time Series Prediction for Graphs in Kernel and Dissimilarity Spaces
We propose to phrase time series prediction as a regression problem and apply dissimilarity- or kernel-based regression techniques, such as 1-nearest neighbor, kernel regression and Gaussian process regression, which can be applied to graphs via graph kernels.
Feasibility Based Large Margin Nearest Neighbor Metric Learning
In this paper, we address the feasibility of LMNN's optimization constraints regarding these target points, and introduce a mathematical measure to evaluate the size of the feasible region of the optimization problem.
Efficient Metric Learning for the Analysis of Motion Data
We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data.
Optimum Reject Options for Prototype-based Classification
We analyse optimum reject strategies for prototype-based classifiers and real-valued rejection measures, using the distance of a data point to the closest prototype or probabilistic counterparts.
