Kerstin Bach

Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor

Self-supervised learning for time-series representation aims to reduce reliance on labeled data while maintaining strong downstream performance, yet many existing approaches incur high computational costs or rely on assumptions that do not hold across diverse temporal dynamics. In this work, we introduce Divide and Contrast (Di-COT), an unsupervised framework that avoids data augmentation and multiple encoder passes by contrasting informative substructures within a window rather than individual timesteps. Di-COT stochastically partitions each window into a small number of overlapping sub-blocks per iteration, enabling efficient and meaningful contrast while mitigating false positives during temporal transitions. To further improve scalability, we adopt a contrastive objective whose computation depends on the batch size and the number of sub-blocks, making loss computation independent of sequence length. Extensive experiments on six large-scale real-world datasets, as well as the UCR and UEA benchmarks, demonstrate that Di-COT learns semantically structured and transferable representations, achieving state-of-the-art performance on classification, clustering, $k$NN, and cross-dataset transfer, while substantially reducing training time. The source code is publicly available at https://github.com/sfi-norwai/Di-COT.

Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor

We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether an adaptive margin (eMargin), adjusted based on a predefined similarity threshold, can improve the separation between adjacent but dissimilar time steps and subsequently lead to better performance in downstream tasks. Our study evaluates the impact of this modification on clustering performance and classification in three benchmark datasets. Our findings, however, indicate that achieving high scores on unsupervised clustering metrics does not necessarily imply that the learned embeddings are meaningful or effective in downstream tasks. To be specific, eMargin added to InfoNCE consistently outperforms state-of-the-art baselines in unsupervised clustering metrics, but struggles to achieve competitive results in downstream classification with linear probing. The source code is publicly available at https://github.com/sfi-norwai/eMargin.

Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor

Representation learning for time series using contrastive learning has emerged as a critical technique for improving the performance of downstream tasks. To advance this effective approach, we introduce CaTT (\textit{Contrast All The Time}), a new approach to unsupervised contrastive learning for time series, which takes advantage of dynamics between temporally similar moments more efficiently and effectively than existing methods. CaTT departs from conventional time-series contrastive approaches that rely on data augmentations or selected views. Instead, it uses the full temporal dimension by contrasting all time steps in parallel. This is made possible by a scalable NT-pair formulation, which extends the classic N-pair loss across both batch and temporal dimensions, making the learning process end-to-end and more efficient. CaTT learns directly from the natural structure of temporal data, using repeated or adjacent time steps as implicit supervision, without the need for pair selection heuristics. We demonstrate that this approach produces superior embeddings which allow better performance in downstream tasks. Additionally, training is faster than other contrastive learning approaches, making it suitable for large-scale and real-world time series applications. The source code is publicly available at \href{https://github.com/sfi-norwai/CaTT}{https://github.com/sfi-norwai/CaTT}.

Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach et al.

Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. Despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to trust the forecasts. Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning. However, there have not been empirical applications and extensive comparisons of these tools in the domain of air quality forecasts. Therefore, this work applies state-of-the-art techniques of uncertainty quantification in a real-world setting of air quality forecasts. Through extensive experiments, we describe training probabilistic models and evaluate their predictive uncertainties based on empirical performance, reliability of confidence estimate, and practical applicability. We also propose improving these models using "free" adversarial training and exploiting temporal and spatial correlation inherent in air quality data. Our experiments demonstrate that the proposed models perform better than previous works in quantifying uncertainty in data-driven air quality forecasts. Overall, Bayesian neural networks provide a more reliable uncertainty estimate but can be challenging to implement and scale. Other scalable methods, such as deep ensemble, Monte Carlo (MC) dropout, and stochastic weight averaging-Gaussian (SWAG), can perform well if applied correctly but with different tradeoffs and slight variations in performance metrics. Finally, our results show the practical impact of uncertainty estimation and demonstrate that, indeed, probabilistic models are more suitable for making informed decisions. Code and dataset are available at \url{https://github.com/Abdulmajid-Murad/deep_probabilistic_forecast}

Deepika Verma, Kerstin Bach, Paul Jarle Mork

In this paper, we demonstrate a data-driven methodology for modelling the local similarity measures of various attributes in a dataset. We analyse the spread in the numerical attributes and estimate their distribution using polynomial function to showcase an approach for deriving strong initial value ranges of numerical attributes and use a non-overlapping distribution for categorical attributes such that the entire similarity range [0,1] is utilized. We use an open source dataset for demonstrating modelling and development of the similarity measures and will present a case-based reasoning (CBR) system that can be used to search for the most relevant similar cases.

Maciej Mozolewski, Betül Bayrak, Kerstin Bach et al.

In eXplainable Artificial Intelligence (XAI), instance-based explanations for time series have gained increasing attention due to their potential for actionable and interpretable insights in domains such as healthcare. Addressing the challenges of explainability of state-of-the-art models, we propose a prototype-driven framework for generating sparse counterfactual explanations tailored to 12-lead ECG classification models. Our method employs SHAP-based thresholds to identify critical signal segments and convert them into interval rules, uses Dynamic Time Warping (DTW) and medoid clustering to extract representative prototypes, and aligns these prototypes to query R-peaks for coherence with the sample being explained. The framework generates counterfactuals that modify only 78% of the original signal while maintaining 81.3% validity across all classes and achieving 43% improvement in temporal stability. We evaluate three variants of our approach, Original, Sparse, and Aligned Sparse, with class-specific performance ranging from 98.9% validity for myocardial infarction (MI) to challenges with hypertrophy (HYP) detection (13.2%). This approach supports near realtime generation (< 1 second) of clinically valid counterfactuals and provides a foundation for interactive explanation platforms. Our findings establish design principles for physiologically-aware counterfactual explanations in AI-based diagnosis systems and outline pathways toward user-controlled explanation interfaces for clinical deployment.

Kerstin Bach, Paul Jarle Mork

During the early stages of developing Case-Based Reasoning (CBR) systems the definition of similarity measures is challenging since this task requires transferring implicit knowledge of domain experts into knowledge representations. While an entire CBR system is very explanatory, the similarity measure determines the ranking but do not necessarily show which features contribute to high (or low) rankings. In this paper we present our work on opening the knowledge engineering process for similarity modelling. This work present is a result of an interdisciplinary research collaboration between AI and public health researchers developing e-Health applications. During this work explainability and transparency of the development process is crucial to allow in-depth quality assurance of the by the domain experts.

Bjørn Magnus Mathisen, Kerstin Bach, Espen Meidell et al.

Identifying individual salmon can be very beneficial for the aquaculture industry as it enables monitoring and analyzing fish behavior and welfare. For aquaculture researchers identifying individual salmon is imperative to their research. The current methods of individual salmon tagging and tracking rely on physical interaction with the fish. This process is inefficient and can cause physical harm and stress for the salmon. In this paper we propose FishNet, based on a deep learning technique that has been successfully used for identifying humans, to identify salmon.We create a dataset of labeled fish images and then test the performance of the FishNet architecture. Our experiments show that this architecture learns a useful representation based on images of salmon heads. Further, we show that good performance can be achieved with relatively small neural network models: FishNet achieves a false positive rate of 1\% and a true positive rate of 96\%.

Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach et al.

In order to make better use of deep reinforcement learning in the creation of sensing policies for resource-constrained IoT devices, we present and study a novel reward function based on the Fisher information value. This reward function enables IoT sensor devices to learn to spend available energy on measurements at otherwise unpredictable moments, while conserving energy at times when measurements would provide little new information. This is a highly general approach, which allows for a wide range of use cases without significant human design effort or hyper-parameter tuning. We illustrate the approach in a scenario of workplace noise monitoring, where results show that the learned behavior outperforms a uniform sampling strategy and comes close to a near-optimal oracle solution.

Bjørn Magnus Mathisen, Agnar Aamodt, Kerstin Bach et al.

Defining similarity measures is a requirement for some machine learning methods. One such method is case-based reasoning (CBR) where the similarity measure is used to retrieve the stored case or set of cases most similar to the query case. Describing a similarity measure analytically is challenging, even for domain experts working with CBR experts. However, data sets are typically gathered as part of constructing a CBR or machine learning system. These datasets are assumed to contain the features that correctly identify the solution from the problem features, thus they may also contain the knowledge to construct or learn such a similarity measure. The main motivation for this work is to automate the construction of similarity measures using machine learning, while keeping training time as low as possible. Our objective is to investigate how to apply machine learning to effectively learn a similarity measure. Such a learned similarity measure could be used for CBR systems, but also for clustering data in semi-supervised learning, or one-shot learning tasks. Recent work has advanced towards this goal, relies on either very long training times or manually modeling parts of the similarity measure. We created a framework to help us analyze current methods for learning similarity measures. This analysis resulted in two novel similarity measure designs. One design using a pre-trained classifier as basis for a similarity measure. The second design uses as little modeling as possible while learning the similarity measure from data and keeping training time low. Both similarity measures were evaluated on 14 different datasets. The evaluation shows that using a classifier as basis for a similarity measure gives state of the art performance. Finally the evaluation shows that our fully data-driven similarity measure design outperforms state of the art methods while keeping training time low.

Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach et al.

Reinforcement learning (RL) is capable of managing wireless, energy-harvesting IoT nodes by solving the problem of autonomous management in non-stationary, resource-constrained settings. We show that the state-of-the-art policy-gradient approaches to RL are appropriate for the IoT domain and that they outperform previous approaches. Due to the ability to model continuous observation and action spaces, as well as improved function approximation capability, the new approaches are able to solve harder problems, permitting reward functions that are better aligned with the actual application goals. We show such a reward function and use policy-gradient approaches to learn capable policies, leading to behavior more appropriate for IoT nodes with less manual design effort, increasing the level of autonomy in IoT.