Sandjai Bhulai

Viktor Zobernig, Richard A. Saldanha, Jinke He et al.

The RangL project hosted by The Alan Turing Institute aims to encourage the wider uptake of reinforcement learning by supporting competitions relating to real-world dynamic decision problems. This article describes the reusable code repository developed by the RangL team and deployed for the 2022 Pathways to Net Zero Challenge, supported by the UK Net Zero Technology Centre. The winning solutions to this particular Challenge seek to optimize the UK's energy transition policy to net zero carbon emissions by 2050. The RangL repository includes an OpenAI Gym reinforcement learning environment and code that supports both submission to, and evaluation in, a remote instance of the open source EvalAI platform as well as all winning learning agent strategies. The repository is an illustrative example of RangL's capability to provide a reusable structure for future challenges.

Etienne van de Bijl, Jan Klein, Joris Pries et al.

Novel prediction methods should always be compared to a baseline to know how well they perform. Without this frame of reference, the performance score of a model is basically meaningless. What does it mean when a model achieves an $F_1$ of 0.8 on a test set? A proper baseline is needed to evaluate the `goodness' of a performance score. Comparing with the latest state-of-the-art model is usually insightful. However, being state-of-the-art can change rapidly when newer models are developed. Contrary to an advanced model, a simple dummy classifier could be used. However, the latter could be beaten too easily, making the comparison less valuable. This paper presents a universal baseline method for all binary classification models, named the Dutch Draw (DD). This approach weighs simple classifiers and determines the best classifier to use as a baseline. We theoretically derive the DD baseline for many commonly used evaluation measures and show that in most situations it reduces to (almost) always predicting either zero or one. Summarizing, the DD baseline is: (1) general, as it is applicable to all binary classification problems; (2) simple, as it is quickly determined without training or parameter-tuning; (3) informative, as insightful conclusions can be drawn from the results. The DD baseline serves two purposes. First, to enable comparisons across research papers by this robust and universal baseline. Secondly, to provide a sanity check during the development process of a prediction model. It is a major warning sign when a model is outperformed by the DD baseline.

Arwin Gansekoele, Emiel Hess, Sandjai Bhulai

The growing privacy concerns surrounding face image data demand new techniques that can guarantee user privacy. One such face recognition technique that claims to achieve better user privacy is Federated Face Recognition (FRR), a subfield of Federated Learning (FL). However, FFR faces challenges due to the heterogeneity of the data, given the large number of classes that need to be handled. To overcome this problem, solutions are sought in the field of personalized FL. This work introduces three new data partitions based on the CelebA dataset, each with a different form of data heterogeneity. It also proposes Hessian-Free Model Agnostic Meta-Learning (HF-MAML) in an FFR setting. We show that HF-MAML scores higher in verification tests than current FFR models on three different CelebA data partitions. In particular, the verification scores improve the most in heterogeneous data partitions. To balance personalization with the development of an effective global model, an embedding regularization term is introduced for the loss function. This term can be combined with HF-MAML and is shown to increase global model verification performance. Lastly, this work performs a fairness analysis, showing that HF-MAML and its embedding regularization extension can improve fairness by reducing the standard deviation over the client evaluation scores.

Joris Pries, Guus Berkelmans, Sandjai Bhulai et al.

Over the past few years, the use of machine learning models has emerged as a generic and powerful means for prediction purposes. At the same time, there is a growing demand for interpretability of prediction models. To determine which features of a dataset are important to predict a target variable $Y$, a Feature Importance (FI) method can be used. By quantifying how important each feature is for predicting $Y$, irrelevant features can be identified and removed, which could increase the speed and accuracy of a model, and moreover, important features can be discovered, which could lead to valuable insights. A major problem with evaluating FI methods, is that the ground truth FI is often unknown. As a consequence, existing FI methods do not give the exact correct FI values. This is one of the many reasons why it can be hard to properly interpret the results of an FI method. Motivated by this, we introduce a new global approach named the Berkelmans-Pries FI method, which is based on a combination of Shapley values and the Berkelmans-Pries dependency function. We prove that our method has many useful properties, and accurately predicts the correct FI values for several cases where the ground truth FI can be derived in an exact manner. We experimentally show for a large collection of FI methods (468) that existing methods do not have the same useful properties. This shows that the Berkelmans-Pries FI method is a highly valuable tool for analyzing datasets with complex interdependencies.

Joris Pries, Etienne van de Bijl, Jan Klein et al.

Before any binary classification model is taken into practice, it is important to validate its performance on a proper test set. Without a frame of reference given by a baseline method, it is impossible to determine if a score is `good' or `bad'. The goal of this paper is to examine all baseline methods that are independent of feature values and determine which model is the `best' and why. By identifying which baseline models are optimal, a crucial selection decision in the evaluation process is simplified. We prove that the recently proposed Dutch Draw baseline is the best input-independent classifier (independent of feature values) for all positional-invariant measures (independent of sequence order) assuming that the samples are randomly shuffled. This means that the Dutch Draw baseline is the optimal baseline under these intuitive requirements and should therefore be used in practice.

Guus Berkelmans, Joris Pries, Sandjai Bhulai et al.

Measuring and quantifying dependencies between random variables (RV's) can give critical insights into a data-set. Typical questions are: `Do underlying relationships exist?', `Are some variables redundant?', and `Is some target variable $Y$ highly or weakly dependent on variable $X$?' Interestingly, despite the evident need for a general-purpose measure of dependency between RV's, common practice of data analysis is that most data analysts use the Pearson correlation coefficient (PCC) to quantify dependence between RV's, while it is well-recognized that the PCC is essentially a measure for linear dependency only. Although many attempts have been made to define more generic dependency measures, there is yet no consensus on a standard, general-purpose dependency function. In fact, several ideal properties of a dependency function have been proposed, but without much argumentation. Motivated by this, in this paper we will discuss and revise the list of desired properties and propose a new dependency function that meets all these requirements. This general-purpose dependency function provides data analysts a powerful means to quantify the level of dependence between variables. To this end, we also provide Python code to determine the dependency function for use in practice.

Hilde I. Hummel, Sandjai Bhulai, Rob D. van der Mei et al.

Increasing levels of anthropogenic noise from ships contribute significantly to underwater sound pollution, posing risks to marine ecosystems. This makes monitoring crucial to understand and quantify the impact of the ship radiated noise. Passive Acoustic Monitoring (PAM) systems are widely deployed for this purpose, generating years of underwater recordings across diverse soundscapes. Manual analysis of such large-scale data is impractical, motivating the need for automated approaches based on machine learning. Recent advances in automatic Underwater Acoustic Target Recognition (UATR) have largely relied on supervised learning, which is constrained by the scarcity of labeled data. Transfer Learning (TL) offers a promising alternative to mitigate this limitation. In this work, we conduct the first empirical comparative study of transfer learning for UATR, evaluating multiple pretrained audio models originating from diverse audio domains. The pretrained model weights are frozen, and the resulting embeddings are analyzed through classification, clustering, and similarity-based evaluations. The analysis shows that the geometrical structure of the embedding space is largely dominated by recording-specific characteristics. However, a simple linear probe can effectively suppress this recording-specific information and isolate ship-type features from these embeddings. As a result, linear probing enables effective automatic UATR using pretrained audio models at low computational cost, significantly reducing the need for a large amounts of high-quality labeled ship recordings.

Erica van der Sar, Alessandro Zocca, Sandjai Bhulai

Recent challenges in operating power networks arise from increasing energy demands and unpredictable renewable sources like wind and solar. While reinforcement learning (RL) shows promise in managing these networks, through topological actions like bus and line switching, efficiently handling large action spaces as networks grow is crucial. This paper presents a hierarchical multi-agent reinforcement learning (MARL) framework tailored for these expansive action spaces, leveraging the power grid's inherent hierarchical nature. Experimental results indicate the MARL framework's competitive performance with single-agent RL methods. We also compare different RL algorithms for lower-level agents alongside different policies for higher-order agents.

Arwin Gansekoele, Tycho Bot, Rob van der Mei et al.

Encryption on the internet with the shift to HTTPS has been an important step to improve the privacy of internet users. However, there is an increasing body of work about extracting information from encrypted internet traffic without having to decrypt it. Such attacks bypass security guarantees assumed to be given by HTTPS and thus need to be understood. Prior works showed that the variable bitrates of video streams are sufficient to identify which video someone is watching. These works generally have to make trade-offs in aspects such as accuracy, scalability, robustness, etc. These trade-offs complicate the practical use of these attacks. To that end, we propose a deep metric learning framework based on the triplet loss method. Through this framework, we achieve robust, generalisable, scalable and transferable encrypted video stream detection. First, the triplet loss is better able to deal with video streams not seen during training. Second, our approach can accurately classify videos not seen during training. Third, we show that our method scales well to a dataset of over 1000 videos. Finally, we show that a model trained on video streams over Chrome can also classify streams over Firefox. Our results suggest that this side-channel attack is more broadly applicable than originally thought. We provide our code alongside a diverse and up-to-date dataset for future research.

Erica van der Sar, Alessandro Zocca, Sandjai Bhulai

Power grid operation is becoming increasingly complex due to the rising integration of renewable energy sources and the need for more adaptive control strategies. Reinforcement Learning (RL) has emerged as a promising approach to power network control (PNC), offering the potential to enhance decision-making in dynamic and uncertain environments. The Learning To Run a Power Network (L2RPN) competitions have played a key role in accelerating research by providing standardized benchmarks and problem formulations, leading to rapid advancements in RL-based methods. This survey provides a comprehensive and structured overview of RL applications for power grid topology optimization, categorizing existing techniques, highlighting key design choices, and identifying gaps in current research. Additionally, we present a comparative numerical study evaluating the impact of commonly applied RL-based methods, offering insights into their practical effectiveness. By consolidating existing research and outlining open challenges, this survey aims to provide a foundation for future advancements in RL-driven power grid optimization.

Arwin Gansekoele, Alexios Balatsoukas-Stimming, Tom Brusse et al.

As telecommunication systems evolve to meet increasing demands, integrating deep neural networks (DNNs) has shown promise in enhancing performance. However, the trade-off between accuracy and flexibility remains challenging when replacing traditional receivers with DNNs. This paper introduces a novel probabilistic framework that allows a single DNN demapper to demap multiple QAM and APSK constellations simultaneously. We also demonstrate that our framework allows exploiting hierarchical relationships in families of constellations. The consequence is that we need fewer neural network outputs to encode the same function without an increase in Bit Error Rate (BER). Our simulation results confirm that our approach approaches the optimal demodulation error bound under an Additive White Gaussian Noise (AWGN) channel for multiple constellations. Thereby, we address multiple important issues in making DNNs flexible enough for practical use as receivers.

Yura Perugachi-Diaz, Arwin Gansekoele, Sandjai Bhulai

Neural image compression has made a great deal of progress. State-of-the-art models are based on variational autoencoders and are outperforming classical models. Neural compression models learn to encode an image into a quantized latent representation that can be efficiently sent to the decoder, which decodes the quantized latent into a reconstructed image. While these models have proven successful in practice, they lead to sub-optimal results due to imperfect optimization and limitations in the encoder and decoder capacity. Recent work shows how to use stochastic Gumbel annealing (SGA) to refine the latents of pre-trained neural image compression models. We extend this idea by introducing SGA+, which contains three different methods that build upon SGA. We show how our method improves the overall compression performance in terms of the R-D trade-off, compared to its predecessors. Additionally, we show how refinement of the latents with our best-performing method improves the compression performance on both the Tecnick and CLIC dataset. Our method is deployed for a pre-trained hyperprior and for a more flexible model. Further, we give a detailed analysis of our proposed methods and show that they are less sensitive to hyperparameter choices. Finally, we show how each method can be extended to three- instead of two-class rounding.

Hilde I. Hummel, Arwin Gansekoele, Sandjai Bhulai et al.

The increasing level of sound pollution in marine environments poses an increased threat to ocean health, making it crucial to monitor underwater noise. By monitoring this noise, the sources responsible for this pollution can be mapped. Monitoring is performed by passively listening to these sounds. This generates a large amount of data records, capturing a mix of sound sources such as ship activities and marine mammal vocalizations. Although machine learning offers a promising solution for automatic sound classification, current state-of-the-art methods implement supervised learning. This requires a large amount of high-quality labeled data that is not publicly available. In contrast, a massive amount of lower-quality unlabeled data is publicly available, offering the opportunity to explore unsupervised learning techniques. This research explores this possibility by implementing an unsupervised Contrastive Learning approach. Here, a Conformer-based encoder is optimized by the so-called Variance-Invariance-Covariance Regularization loss function on these lower-quality unlabeled data and the translation to the labeled data is made. Through classification tasks involving recognizing ship types and marine mammal vocalizations, our method demonstrates to produce robust and generalized embeddings. This shows to potential of unsupervised methods for various automatic underwater acoustic analysis tasks.

Evy Beijen, Pien Pieterse, Yusuf Çelik et al.

Religious language continues to permeate contemporary discourse, even in ostensibly secular domains such as environmental activism and climate change debates. This paper investigates how explicit and implicit forms of religious language appear in climate-related texts produced by secular and religious nongovernmental organizations (NGOs). We introduce a dual methodological approach: a rule-based model using a hierarchical tree of religious terms derived from ecotheology literature, and large language models (LLMs) operating in a zero-shot setting. Using a dataset of more than 880,000 sentences, we compare how these methods detect religious language and analyze points of agreement and divergence. The results show that the rule-based method consistently labels more sentences as religious than LLMs. These findings highlight not only the methodological challenges of computationally detecting religious language but also the broader tension over whether religious language should be defined by vocabulary alone or by contextual meaning. This study contributes to digital methods in religious studies by demonstrating both the potential and the limitations of approaches for analyzing how the sacred persists in climate discourse.

Corné de Ruijt, Sandjai Bhulai

This paper provides a review of the job recommender system (JRS) literature published in the past decade (2011-2021). Compared to previous literature reviews, we put more emphasis on contributions that incorporate the temporal and reciprocal nature of job recommendations. Previous studies on JRS suggest that taking such views into account in the design of the JRS can lead to improved model performance. Also, it may lead to a more uniform distribution of candidates over a set of similar jobs. We also consider the literature from the perspective of algorithm fairness. Here we find that this is rarely discussed in the literature, and if it is discussed, many authors wrongly assume that removing the discriminatory feature would be sufficient. With respect to the type of models used in JRS, authors frequently label their method as `hybrid'. Unfortunately, they thereby obscure what these methods entail. Using existing recommender taxonomies, we split this large class of hybrids into subcategories that are easier to analyse. We further find that data availability, and in particular the availability of click data, has a large impact on the choice of method and validation. Last, although the generalizability of JRS across different datasets is infrequently considered, results suggest that error scores may vary across these datasets.

Corné de Ruijt, Sandjai Bhulai

Given the vital importance of search engines to find digital information, there has been much scientific attention on how users interact with search engines, and how such behavior can be modeled. Many models on user - search engine interaction, which in the literature are known as click models, come in the form of Dynamic Bayesian Networks. Although many authors have used the resemblance between the different click models to derive estimation procedures for these models, in particular in the form of expectation maximization (EM), still this commonly requires considerable work, in particular when it comes to deriving the E-step. What we propose in this paper, is that this derivation is commonly unnecessary: many existing click models can in fact, under certain assumptions, be optimized as they were Input-Output Hidden Markov Models (IO-HMMs), for which the forward-backward equations immediately provide this E-step. To arrive at that conclusion, we will present the Generalized Cascade Model (GCM) and show how this model can be estimated using the IO-HMM EM framework, and provide two examples of how existing click models can be mapped to GCM. Our GCM approach to estimating click models has also been implemented in the gecasmo Python package.

Jan Klein, Sandjai Bhulai, Mark Hoogendoorn et al.

Over the past decade, the advent of cybercrime has accelarated the research on cybersecurity. However, the deployment of intrusion detection methods falls short. One of the reasons for this is the lack of realistic evaluation datasets, which makes it a challenge to develop techniques and compare them. This is caused by the large amounts of effort it takes for a cyber analyst to classify network connections. This has raised the need for methods (i) that can learn from small sets of labeled data, (ii) that can make predictions on large sets of unlabeled data, and (iii) that request the label of only specially selected unlabeled data instances. Hence, Active Learning (AL) methods are of interest. These approaches choose specific unlabeled instances by a query function that are expected to improve overall classification performance. The resulting query observations are labeled by a human expert and added to the labeled set. In this paper, we propose a new hybrid AL method called Jasmine. Firstly, it determines how suitable each observation is for querying, i.e., how likely it is to enhance classification. These properties are the uncertainty score and anomaly score. Secondly, Jasmine introduces dynamic updating. This allows the model to adjust the balance between querying uncertain, anomalous and randomly selected observations. To this end, Jasmine is able to learn the best query strategy during the labeling process. This is in contrast to the other AL methods in cybersecurity that all have static, predetermined query functions. We show that dynamic updating, and therefore Jasmine, is able to consistently obtain good and more robust results than querying only uncertainties, only anomalies or a fixed combination of the two.

Yura Perugachi-Diaz, Jakub M. Tomczak, Sandjai Bhulai

We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient extension of Residual Flows. The method relies on an analysis of the Lipschitz continuity of the concatenation in DenseNets, where we enforce invertibility of the network by satisfying the Lipschitz constant. Furthermore, we propose a learnable weighted concatenation, which not only improves the model performance but also indicates the importance of the concatenated weighted representation. Additionally, we introduce the Concatenated LipSwish as activation function, for which we show how to enforce the Lipschitz condition and which boosts performance. The new architecture, i-DenseNet, out-performs Residual Flow and other flow-based models on density estimation evaluated in bits per dimension, where we utilize an equal parameter budget. Moreover, we show that the proposed model out-performs Residual Flows when trained as a hybrid model where the model is both a generative and a discriminative model.

Yura Perugachi-Diaz, Jakub M. Tomczak, Sandjai Bhulai

We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient alternative to Residual Flows. The method relies on an analysis of the Lipschitz continuity of the concatenation in DenseNets, where we enforce the invertibility of the network by satisfying the Lipschitz constraint. Additionally, we extend this method by proposing a learnable concatenation, which not only improves the model performance but also indicates the importance of the concatenated representation. We demonstrate the performance of i-DenseNets and Residual Flows on toy, MNIST, and CIFAR10 data. Both i-DenseNets outperform Residual Flows evaluated in negative log-likelihood, on all considered datasets under an equal parameter budget.