Author name cluster

Thomas Villmann

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.

5 papers

1 author row

AAAI Conference 2025 Conference Paper

A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations

Sascha Saralajew
Ashish Rana
Thomas Villmann
Ammar Shaker

Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called deep Prototype-Based Networks (PBNs), also known as prototypical parts models. In this work, we analyze these models with respect to different properties, including interpretability. In particular, we focus on the Classification-by-Components (CBC) approach, which uses a probabilistic model to ensure interpretability and can be used as a shallow or deep architecture. We show that this model has several shortcomings, like creating contradicting explanations. Based on these findings, we propose an extension of CBC that solves these issues. Moreover, we prove that this extension has robustness guarantees and derive a loss that optimizes robustness. Additionally, our analysis shows that most (deep) PBNs are related to (deep) RBF classifiers, which implies that our robustness guarantees generalize to shallow RBF classifiers. The empirical evaluation demonstrates that our deep PBN yields state-of-the-art classification accuracy on different benchmarks while resolving the interpretability shortcomings of other approaches. Further, our shallow PBN variant outperforms other shallow PBNs while being inherently interpretable and exhibiting provable robustness guarantees.

PDF Details DOI

AIIM Journal 2024 Journal Article

Subspace corrected relevance learning with application in neuroimaging

Rick van Veen
Neha Rajendra Bari Tamboli
Sofie Lövdal
Sanne K. Meles
Remco J. Renken
Gert-Jan de Vries
Dario Arnaldi
Silvia Morbelli

In machine learning, data often comes from different sources, but combining them can introduce extraneous variation that affects both generalization and interpretability. For example, we investigate the classification of neurodegenerative diseases using FDG-PET data collected from multiple neuroimaging centers. However, data collected at different centers introduces unwanted variation due to differences in scanners, scanning protocols, and processing methods. To address this issue, we propose a two-step approach to limit the influence of center-dependent variation on the classification of healthy controls and early vs. late-stage Parkinson’s disease patients. First, we train a Generalized Matrix Learning Vector Quantization (GMLVQ) model on healthy control data to identify a “relevance space” that distinguishes between centers. Second, we use this space to construct a correction matrix that restricts a second GMLVQ system’s training on the diagnostic problem. We evaluate the effectiveness of this approach on the real-world multi-center datasets and simulated artificial dataset. Our results demonstrate that the approach produces machine learning systems with reduced bias - being more specific due to eliminating information related to center differences during the training process - and more informative relevance profiles that can be interpreted by medical experts. This method can be adapted to similar problems outside the neuroimaging domain, as long as an appropriate “relevance space” can be identified to construct the correction matrix.

Details DOI

NeurIPS Conference 2020 Conference Paper

Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms

Sascha Saralajew
Lars Holdijk
Thomas Villmann

Methods for adversarial robustness certification aim to provide an upper bound on the test error of a classifier under adversarial manipulation of its input. Current certification methods are computationally expensive and limited to attacks that optimize the manipulation with respect to a norm. We overcome these limitations by investigating the robustness properties of Nearest Prototype Classifiers (NPCs) like learning vector quantization and large margin nearest neighbor. For this purpose, we study the hypothesis margin. We prove that if NPCs use a dissimilarity measure induced by a seminorm, the hypothesis margin is a tight lower bound on the size of adversarial attacks and can be calculated in constant time—this provides the first adversarial robustness certificate calculable in reasonable time. Finally, we show that each NPC trained by a triplet loss maximizes the hypothesis margin and is therefore optimized for adversarial robustness. In the presented evaluation, we demonstrate that NPCs optimized for adversarial robustness are competitive with state-of-the-art methods and set a new benchmark with respect to computational complexity for robustness certification.

PDF Details

NeurIPS Conference 2019 Conference Paper

Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components

Sascha Saralajew
Lars Holdijk
Maike Rees
Ebubekir Asan
Thomas Villmann

Abstract Neural networks are state-of-the-art classification approaches but are generally difficult to interpret. This issue can be partly alleviated by constructing a precise decision process within the neural network. In this work, a network architecture, denoted as Classification-By-Components network (CBC), is proposed. It is restricted to follow an intuitive reasoning based decision process inspired by Biederman's recognition-by-components theory from cognitive psychology. The network is trained to learn and detect generic components that characterize objects. In parallel, a class-wise reasoning strategy based on these components is learned to solve the classification problem. In contrast to other work on reasoning, we propose three different types of reasoning: positive, negative, and indefinite. These three types together form a probability space to provide a probabilistic classifier. The decomposition of objects into generic components combined with the probabilistic reasoning provides by design a clear interpretation of the classification decision process. The evaluation of the approach on MNIST shows that CBCs are viable classifiers. Additionally, we demonstrate that the inherent interpretability offers a profound understanding of the classification behavior such that we can explain the success of an adversarial attack. The method's scalability is successfully tested using the ImageNet dataset.

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