Arrow Research search

Author name cluster

Barbara Hammer

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers
2 author rows

Possible papers

17

NeurIPS Conference 2025 Conference Paper

AI-Generated Video Detection via Perceptual Straightening

  • Christian Internò
  • Robert Geirhos
  • Markus Olhofer
  • Sunny Liu
  • Barbara Hammer
  • David Klindt

The rapid advancement of generative AI enables highly realistic synthetic video, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection methods often struggle with generalization and capturing subtle temporal inconsistencies. We propose $ReStraV$ ($Re$presentation $Stra$ightening for $V$ideo), a novel approach to distinguish natural from AI-generated videos. Inspired by the ``perceptual straightening'' hypothesis—which suggests real-world video trajectories become more straight in neural representation domain—we analyze deviations from this expected geometric property. Using a pre-trained self-supervised vision transformer (DINOv2), we quantify the temporal curvature and stepwise distance in the model's representation domain. We aggregate statistical and signals descriptors of these measures for each video and train a classifier. Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos. A lightweight classifier achieves state-of-the-art detection performance (e. g. , $97. 17$ % accuracy and $98. 63$ % AUROC on the VidProM benchmark, substantially outperforming existing image- and video-based methods. ReStraV is computationally efficient, it is offering a low-cost and effective detection solution. This work provides new insights into using neural representation geometry for AI-generated video detection.

PDF Details

ICLR Conference 2025 Conference Paper

Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks

  • Maximilian Muschalik
  • Fabian Fumagalli
  • Paolo Frazzetto
  • Janine Strotherm
  • Luca Hermes
  • Alessandro Sperduti
  • Eyke Hüllermeier
  • Barbara Hammer

Albeit the ubiquitous use of Graph Neural Networks (GNNs) in machine learning (ML) prediction tasks involving graph-structured data, their interpretability remains challenging. In explainable artificial intelligence (XAI), the Shapley Value (SV) is the predominant method to quantify contributions of individual features to a ML model’s output. Addressing the limitations of SVs in complex prediction models, Shapley Interactions (SIs) extend the SV to groups of features. In this work, we explain single graph predictions of GNNs with SIs that quantify node contributions and interactions among multiple nodes. By exploiting the GNN architecture, we show that the structure of interactions in node embeddings are preserved for graph prediction. As a result, the exponential complexity of SIs depends only on the receptive fields, i.e. the message-passing ranges determined by the connectivity of the graph and the number of convolutional layers. Based on our theoretical results, we introduce GraphSHAP-IQ, an efficient approach to compute any-order SIs exactly. GraphSHAP-IQ is applicable to popular message passing techniques in conjunction with a linear global pooling and output layer. We showcase that GraphSHAP-IQ substantially reduces the exponential complexity of computing exact SIs on multiple benchmark datasets. Beyond exact computation, we evaluate GraphSHAP-IQ’s approximation of SIs on popular GNN architectures and compare with existing baselines. Lastly, we visualize SIs of real-world water distribution networks and molecule structures using a SI-Graph.

Details

NeurIPS Conference 2025 Conference Paper

Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions

  • Hubert Baniecki
  • Maximilian Muschalik
  • Fabian Fumagalli
  • Barbara Hammer
  • Eyke Hüllermeier
  • Przemyslaw Biecek

Language-image pre-training (LIP) enables the development of vision-language models capable of zero-shot classification, localization, multimodal retrieval, and semantic understanding. Various explanation methods have been proposed to visualize the importance of input image-text pairs on the model's similarity outputs. However, popular saliency maps are limited by capturing only first-order attributions, overlooking the complex cross-modal interactions intrinsic to such encoders. We introduce faithful interaction explanations of LIP models (FIxLIP) as a unified approach to decomposing the similarity in vision-language encoders. FIxLIP is rooted in game theory, where we analyze how using the weighted Banzhaf interaction index offers greater flexibility and improves computational efficiency over the Shapley interaction quantification framework. From a practical perspective, we propose how to naturally extend explanation evaluation metrics, such as the pointing game and area between the insertion/deletion curves, to second-order interaction explanations. Experiments on the MS COCO and ImageNet-1k benchmarks validate that second-order methods, such as FIxLIP, outperform first-order attribution methods. Beyond delivering high-quality explanations, we demonstrate the utility of FIxLIP in comparing different models, e. g. CLIP vs. SigLIP-2.

PDF Details

AAAI Conference 2024 Conference Paper

Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles

  • Maximilian Muschalik
  • Fabian Fumagalli
  • Barbara Hammer
  • Eyke Hüllermeier

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. As a remedy, the Shapley value (SV) is a well-known concept in explainable artificial intelligence (XAI) research for quantifying additive feature attributions of predictions. The model-specific TreeSHAP methodology solves the exponential complexity for retrieving exact SVs from tree-based models. Expanding beyond individual feature attribution, Shapley interactions reveal the impact of intricate feature interactions of any order. In this work, we present TreeSHAP-IQ, an efficient method to compute any-order additive Shapley interactions for predictions of tree-based models. TreeSHAP-IQ is supported by a mathematical framework that exploits polynomial arithmetic to compute the interaction scores in a single recursive traversal of the tree, akin to Linear TreeSHAP. We apply TreeSHAP-IQ on state-of-the-art tree ensembles and explore interactions on well-established benchmark datasets.

PDF Details DOI

ICML Conference 2024 Conference Paper

KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions

  • Fabian Fumagalli
  • Maximilian Muschalik
  • Patrick Kolpaczki
  • Eyke Hüllermeier
  • Barbara Hammer

The Shapley value (SV) is a prevalent approach of allocating credit to machine learning (ML) entities to understand black box ML models. Enriching such interpretations with higher-order interactions is inevitable for complex systems, where the Shapley Interaction Index (SII) is a direct axiomatic extension of the SV. While it is well-known that the SV yields an optimal approximation of any game via a weighted least square (WLS) objective, an extension of this result to SII has been a long-standing open problem, which even led to the proposal of an alternative index. In this work, we characterize higher-order SII as a solution to a WLS problem, which constructs an optimal approximation via SII and k-Shapley values (k-SII). We prove this representation for the SV and pairwise SII and give empirically validated conjectures for higher orders. As a result, we propose KernelSHAP-IQ, a direct extension of KernelSHAP for SII, and demonstrate state-of-the-art performance for feature interactions.

Details

AAAI Conference 2024 Conference Paper

Physics-Informed Graph Neural Networks for Water Distribution Systems

  • Inaam Ashraf
  • Janine Strotherm
  • Luca Hermes
  • Barbara Hammer

Water distribution systems (WDS) are an integral part of critical infrastructure which is pivotal to urban development. As 70% of the world's population will likely live in urban environments in 2050, efficient simulation and planning tools for WDS play a crucial role in reaching UN's sustainable developmental goal (SDG) 6 - "Clean water and sanitation for all". 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. Using a recursive approach, our model only needs a few graph convolutional neural network (GCN) layers and employs an innovative algorithm based on message passing. Unlike conventional machine learning tasks, the model uses hydraulic principles to infer two additional hydraulic state features in the process of reconstructing the available ground truth feature in an unsupervised manner. To the best of our knowledge, this is the first DL approach to emulate the popular hydraulic simulator EPANET, utilizing no additional information. Like most DL models and unlike the hydraulic simulator, our model demonstrates vastly faster emulation times that do not increase drastically with the size of the WDS. Moreover, we achieve high accuracy on the ground truth and very similar results compared to the hydraulic simulator as demonstrated through experiments on five real-world WDS datasets.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

shapiq: Shapley Interactions for Machine Learning

  • Maximilian Muschalik
  • Hubert Baniecki
  • Fabian Fumagalli
  • Patrick Kolpaczki
  • Barbara Hammer
  • Eyke Hüllermeier

Originally rooted in game theory, the Shapley Value (SV) has recently become an important tool in machine learning research. Perhaps most notably, it is used for feature attribution and data valuation in explainable artificial intelligence. Shapley Interactions (SIs) naturally extend the SV and address its limitations by assigning joint contributions to groups of entities, which enhance understanding of black box machine learning models. Due to the exponential complexity of computing SVs and SIs, various methods have been proposed that exploit structural assumptions or yield probabilistic estimates given limited resources. In this work, we introduce shapiq, an open-source Python package that unifies state-of-the-art algorithms to efficiently compute SVs and any-order SIs in an application-agnostic framework. Moreover, it includes a benchmarking suite containing 11 machine learning applications of SIs with pre-computed games and ground-truth values to systematically assess computational performance across domains. For practitioners, shapiq is able to explain and visualize any-order feature interactions in predictions of models, including vision transformers, language models, as well as XGBoost and LightGBM with TreeSHAP-IQ. With shapiq, we extend shap beyond feature attributions and consolidate the application of SVs and SIs in machine learning that facilitates future research. The source code and documentation are available at https: //github. com/mmschlk/shapiq.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

SHAP-IQ: Unified Approximation of any-order Shapley Interactions

  • Fabian Fumagalli
  • Maximilian Muschalik
  • Patrick Kolpaczki
  • Eyke Hüllermeier
  • Barbara Hammer

Predominately in explainable artificial intelligence (XAI) research, the Shapley value (SV) is applied to determine feature attributions for any black box model. Shapley interaction indices extend the SV to define any-order feature interactions. Defining a unique Shapley interaction index is an open research question and, so far, three definitions have been proposed, which differ by their choice of axioms. Moreover, each definition requires a specific approximation technique. Here, we propose SHAPley Interaction Quantification (SHAP-IQ), an efficient sampling-based approximator to compute Shapley interactions for arbitrary cardinal interaction indices (CII), i. e. interaction indices that satisfy the linearity, symmetry and dummy axiom. SHAP-IQ is based on a novel representation and, in contrast to existing methods, we provide theoretical guarantees for its approximation quality, as well as estimates for the variance of the point estimates. For the special case of SV, our approach reveals a novel representation of the SV and corresponds to Unbiased KernelSHAP with a greatly simplified calculation. We illustrate the computational efficiency and effectiveness by explaining language, image classification and high-dimensional synthetic models.

PDF Details

ICLR Conference 2021 Conference Paper

Graph Edit Networks

  • Benjamin Paaßen
  • Daniele Grattarola
  • Daniele Zambon
  • Cesare Alippi
  • Barbara Hammer

While graph neural networks have made impressive progress in classification and regression, few approaches to date perform time series prediction on graphs, and those that do are mostly limited to edge changes. We suggest that graph edits are a more natural interface for graph-to-graph learning. In particular, graph edits are general enough to describe any graph-to-graph change, not only edge changes; they are sparse, making them easier to understand for humans and more efficient computationally; and they are local, avoiding the need for pooling layers in graph neural networks. In this paper, we propose a novel output layer - the graph edit network - which takes node embeddings as input and generates a sequence of graph edits that transform the input graph to the output graph. We prove that a mapping between the node sets of two graphs is sufficient to construct training data for a graph edit network and that an optimal mapping yields edit scripts that are almost as short as the graph edit distance between the graphs. We further provide a proof-of-concept empirical evaluation on several graph dynamical systems, which are difficult to learn for baselines from the literature.

Details

IJCAI Conference 2020 Conference Paper

DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction

  • Alexander Schulz
  • Fabian Hinder
  • Barbara Hammer

Machine learning algorithms using deep architectures have been able to implement increasingly powerful and successful models. However, they also become increasingly more complex, more difficult to comprehend and easier to fool. So far, most methods in the literature investigate the decision of the model for a single given input datum. In this paper, we propose to visualize a part of the decision function of a deep neural network together with a part of the data set in two dimensions with discriminative dimensionality reduction. This enables us to inspect how different properties of the data are treated by the model, such as outliers, adversaries or poisoned data. Further, the presented approach is complementary to the mentioned interpretation methods from the literature and hence might be even more useful in combination with those. Code is available at https: //github. com/LucaHermes/DeepView

PDF Details DOI

ICML Conference 2020 Conference Paper

Towards Non-Parametric Drift Detection via Dynamic Adapting Window Independence Drift Detection (DAWIDD)

  • Fabian Hinder
  • André Artelt
  • Barbara Hammer

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. Many online learning schemes include drift detection to actively detect and react to observed changes. Yet, reliable drift detection constitutes a challenging problem in particular in the context of high dimensional data, varying drift characteristics, and the absence of a parametric model such as a classification scheme which reflects the drift. In this paper we present a novel concept drift detection method, Dynamic Adapting Window Independence Drift Detection (DAWIDD), which aims for non-parametric drift detection of diverse drift characteristics. For this purpose, we establish a mathematical equivalence of the presence of drift to the dependency of specific random variables in an according drift process. This allows us to rely on independence tests rather than parametric models or the classification loss, resulting in a fairly robust scheme to universally detect different types of drift, as it is also confirmed in experiments.

Details

ICRA Conference 2019 Conference Paper

Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units

  • Viktor Losing
  • Taizo Yoshikawa
  • Martina Hasenjäger
  • Barbara Hammer
  • Heiko Wersing

Online action classification is an important field of research, enabling the particularly interesting application scenario of controlling wearable devices which actively support the user's motions. The majority of machine learning applications of real-world systems are based on pre-trained average-user models without any personalization. Our long-term goal is to provide a system that adapts to its user's personal behavior patterns on the fly and in real-time. Ideally, we want to initiate a continuous collaboration between the system and the user where both alternatively adjust to each other to maximize the system's utility. Such tasks are not feasible with static models. In this paper, we investigate the potential and benefits of personalized online learning in the task of online action classification. We record motion sequences of different subjects wearing the Xsens bodysuit, which incorporates multiple inertial measuring units, enabling a fine-grained discrimination of motions. On this basis, we first perform a feature selection, showing that only a few sensors are necessary to achieve a high classification performance. Subsequently, we compare the recognition capabilities of offline average user models against personalized models trained in an online way. Our experiments conclude that personalized models require only few data to outperform average user systems and are particularly valuable for applications with limited computational hardware which rely on the raw sensor inputs only.

Details

ICML Conference 2018 Conference Paper

Tree Edit Distance Learning via Adaptive Symbol Embeddings

  • Benjamin Paaßen
  • Claudio Gallicchio
  • Alessio Micheli
  • Barbara Hammer

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. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i. e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300, 000 nodes.

Details

IJCAI Conference 2017 Conference Paper

Self-Adjusting Memory: How to Deal with Diverse Drift Types

  • Viktor Losing
  • Barbara Hammer
  • Heiko Wersing

Data Mining in non-stationary data streams is particularly relevant in the context of the Internet of Things and Big Data. Its challenges arise from fundamentally different drift types violating assumptions of data independence or stationarity. Available methods often struggle with certain forms of drift or require unavailable a priori task knowledge. We propose the Self-Adjusting Memory (SAM) model for the k Nearest Neighbor (kNN) algorithm. SAM-kNN can deal with heterogeneous concept drift, i. e. different drift types and rates. Its basic idea are dedicated models for current and former concepts used according to the demands of the given situation. It can be robustly applied in practice without meta parameter optimization. We conduct an extensive evaluation on various benchmarks, consisting of artificial streams with known drift characteristics and real-world datasets. Highly competitive results throughout all experiments underline the robustness of SAM-kNN as well as its capability to handle heterogeneous concept drift.

PDF Details

AIIM Journal 2009 Journal Article

Cancer informatics by prototype networks in mass spectrometry

  • Frank-Michael Schleif
  • Thomas Villmann
  • Markus Kostrzewa
  • Barbara Hammer
  • Alexander Gammerman

Objective Mass spectrometry has become a standard technique to analyze clinical samples in cancer research. The obtained spectrometric measurements reveal a lot of information of the clinical sample at the peptide and protein level. The spectra are high dimensional and, due to the small number of samples a sparse coverage of the population is very common. In clinical research the calculation and evaluation of classification models is important. For classical statistics this is achieved by hypothesis testing with respect to a chosen level of confidence. In clinical proteomics the application of statistical tests is limited due to the small number of samples and the high dimensionality of the data. Typically soft methods from the field of machine learning are used to generate such models. However for these methods no or only few additional information about the safety of the model decision is available. In this contribution the spectral data are processed as functional data and conformal classifier models are generated. The obtained models allow the detection of potential biomarker candidates and provide confidence measures for the classification decision. Methods First, wavelet-based techniques for the efficient processing and encoding of mass spectrometric measurements from clinical samples are presented. A prototype-based classifier is extended by a functional metric and combined with the concept of conformal prediction to classify the clinical proteomic spectra and to evaluate the results. Results Clinical proteomic data of a colorectal cancer and a lung cancer study are used to test the performance of the proposed algorithm. The prototype classifiers are evaluated with respect to prediction accuracy and the confidence of the classification decisions. The adapted metric parameters are analyzed and interpreted to find potential biomarker candidates. Conclusions The proposed algorithm can be used to analyze functional data as obtained from clinical mass spectrometry, to find discriminating mass positions and to judge the confidence of the obtained classifications, providing robust and interpretable classification models.

Details DOI

JMLR Journal 2007 Journal Article

Dynamics and Generalization Ability of LVQ Algorithms

  • Michael Biehl
  • Anarta Ghosh
  • Barbara Hammer

Learning vector quantization (LVQ) schemes constitute intuitive, powerful classification heuristics with numerous successful applications but, so far, limited theoretical background. We study LVQ rigorously within a simplifying model situation: two competing prototypes are trained from a sequence of examples drawn from a mixture of Gaussians. Concepts from statistical physics and the theory of on-line learning allow for an exact description of the training dynamics in high-dimensional feature space. The analysis yields typical learning curves, convergence properties, and achievable generalization abilities. This is also possible for heuristic training schemes which do not relate to a cost function. We compare the performance of several algorithms, including Kohonen's LVQ1 and LVQ+/-, a limiting case of LVQ2.1. The former shows close to optimal performance, while LVQ+/- displays divergent behavior. We investigate how early stopping can overcome this difficulty. Furthermore, we study a crisp version of robust soft LVQ, which was recently derived from a statistical formulation. Surprisingly, it exhibits relatively poor generalization. Performance improves if a window for the selection of data is introduced; the resulting algorithm corresponds to cost function based LVQ2. The dependence of these results on the model parameters, for example, prior class probabilities, is investigated systematically, simulations confirm our analytical findings. [abs] [ pdf ][ bib ] &copy JMLR 2007. ( edit, beta )

PDF Details

TCS Journal 2005 Journal Article

On approximate learning by multi-layered feedforward circuits

  • Bhaskar DasGupta
  • Barbara Hammer

We deal with the problem of efficient learning of feedforward neural networks. First, we consider the objective to maximize the ratio of correctly classified points compared to the size of the training set. We show that it is NP-hard to approximate the ratio within some constant relative error if architectures with varying input dimension, one hidden layer, and two hidden neurons are considered where the activation function in the hidden layer is the sigmoid function, and the situation of epsilon-separation is assumed, or the activation function is the semilinear function. For single hidden layer threshold networks with varying input dimension and n hidden neurons, approximation within a relative error depending on n is NP-hard even if restricted to situations where the number of examples is limited with respect to n. Afterwards, we consider the objective to minimize the failure ratio in the presence of misclassification errors. We show that it is NP-hard to approximate the failure ratio within any positive constant for a multilayered threshold network with varying input dimension and a fixed number of neurons in the hidden layer if the thresholds of the neurons in the first hidden layer are zero. Furthermore, even obtaining weak approximations is almost NP-hard in the same situation.

Details DOI