Out-of-distribution (OOD) detection is essential for ensuring the reliability of deep learning models operating in open-world scenarios. Current OOD detectors mainly rely on statistical models to identify unusual patterns in the latent representations of a deep neural network. This work proposes to augment existing OOD detectors with probabilistic reasoning, utilizing Markov logic networks (MLNs). MLNs connect first-order logic with probabilistic reasoning to assign probabilities to inputs based on weighted logical constraints defined over human-understandable concepts, which offers improved explainability. Through extensive experiments on multiple datasets, we demonstrate that MLNs can significantly enhance the performance of a wide range of existing OOD detectors while maintaining computational efficiency. Furthermore, we introduce a simple algorithm for learning logical constraints for OOD detection from a dataset and showcase its effectiveness.

Machine Learning models often only generalize reliably to samples from the training distribution. Consequentially, detecting when input data is out-of-distribution (OOD) is crucial, especially in safety-critical applications. Current OOD detection methods, however, tend to be domain agnostic and often fail to incorporate valuable prior knowledge about the structure of the training distribution. To address this limitation, we introduce a novel, hybrid OOD detection algorithm that combines a deep learning-based perception system with a first-order logic-based knowledge representation. A logical reasoning system uses this knowledge base at run-time to infer whether inputs are consistent with prior knowledge about the training distribution. In contrast to purely neural systems, the structured knowledge representation allows humans to inspect and modify the rules that govern the OOD detectors’ behavior. This not only enhances performance but also fosters a level of explainability that is particularly beneficial in safety-critical contexts. We demonstrate the effectiveness of our method through experiments on several datasets and discuss advantages and limitations. Our code is available online.1

The performance of machine learning models can be significantly impacted by variations in data quality. Typically, conventional model testing does not examine how robust the model would be in the face of potential data quality deterioration. In an industrial use case, however, data quality is a pertinent issue, as sensors are susceptible to a variety of technical and external issues that may result in poor data quality over time. In order to develop robust machine learning models, industrial data scientists must understand the sensitivity of their models against data quality issues, through the application of an appropriate and comprehensive testing solution. In this work, we propose a generic framework for systematically analyzing the impact of data quality issues on the performance of machine learning models by intentionally applying gradual perturbations to the original time series data. The evaluation is performed using a benchmark industrial process consisting of multivariate time series from sensors in a complex chemical process.

Machine learning-based classification algorithms typically operate under assumptions that assert that the underlying data generating distribution is stationary and draws from a finite set of categories. In some scenarios, these assumptions might not hold, but identifying violating inputs - here referred to as anomalies - is a challenging task. Recent publications propose deep learning-based approaches that perform anomaly detection and classification jointly by (implicitly) learning a mapping that projects data points to a lower-dimensional space, such that the images of points of one class reside inside of a hypersphere, while others are mapped outside of it. In this work, we propose Multi-Class Hypersphere Anomaly Detection (MCHAD), a new hypersphere learning algorithm for anomaly detection in classification settings, as well as a generalization of existing hypersphere learning methods that allows incorporating example anomalies into the training. Extensive experiments on competitive benchmark tasks, as well as theoretical arguments, provide evidence for the effectiveness of our method. Our code is publicly available1.

Data exchange and integration in a heterogeneous engineering network are challenges that an engineering organi-zation has to address. Most practitioners have realized that this challenge requires detailed consideration and involvement of the related engineering disciplines to specify and implement an appropriate data logistics. In this paper, we introduce a meta-model and method for the development of a data-mapping infrastructure to support the work of the engineers responsible for data logistics. The meta-model is the foundation for data logistics with automated data transformation, integration, and exchange by automating the mapping of engineering data as envisioned in VDI Guideline 3695. We report on a first validation of the method with a proof of concept using AutomationML.