Eirini Ntoutsi

Vasileios Iosifidis, Symeon Papadopoulos, Bodo Rosenhahn et al.

Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating the classes differently, formulated typically via a user-defined fixed misclassification cost matrix provided as input to the learner. Such parameter tuning is a challenging task that requires domain knowledge and moreover, wrong adjustments might lead to overall predictive performance deterioration. In this work, we propose a novel cost-sensitive boosting approach for imbalanced data that dynamically adjusts the misclassification costs over the boosting rounds in response to model's performance instead of using a fixed misclassification cost matrix. Our method, called AdaCC, is parameter-free as it relies on the cumulative behavior of the boosting model in order to adjust the misclassification costs for the next boosting round and comes with theoretical guarantees regarding the training error. Experiments on 27 real-world datasets from different domains with high class imbalance demonstrate the superiority of our method over 12 state-of-the-art cost-sensitive boosting approaches exhibiting consistent improvements in different measures, for instance, in the range of [0.3%-28.56%] for AUC, [3.4%-21.4%] for balanced accuracy, [4.8%-45%] for gmean and [7.4%-85.5%] for recall.

Yi Cai, Arthur Zimek, Gerhard Wunder et al.

Hate speech detection is a common downstream application of natural language processing (NLP) in the real world. In spite of the increasing accuracy, current data-driven approaches could easily learn biases from the imbalanced data distributions originating from humans. The deployment of biased models could further enhance the existing social biases. But unlike handling tabular data, defining and mitigating biases in text classifiers, which deal with unstructured data, are more challenging. A popular solution for improving machine learning fairness in NLP is to conduct the debiasing process with a list of potentially discriminated words given by human annotators. In addition to suffering from the risks of overlooking the biased terms, exhaustively identifying bias with human annotators are unsustainable since discrimination is variable among different datasets and may evolve over time. To this end, we propose an automatic misuse detector (MiD) relying on an explanation method for detecting potential bias. And built upon that, an end-to-end debiasing framework with the proposed staged correction is designed for text classifiers without any external resources required.

Arjun Roy, Jan Horstmann, Eirini Ntoutsi

AI-driven decision-making can lead to discrimination against certain individuals or social groups based on protected characteristics/attributes such as race, gender, or age. The domain of fairness-aware machine learning focuses on methods and algorithms for understanding, mitigating, and accounting for bias in AI/ML models. Still, thus far, the vast majority of the proposed methods assess fairness based on a single protected attribute, e.g. only gender or race. In reality, though, human identities are multi-dimensional, and discrimination can occur based on more than one protected characteristic, leading to the so-called ``multi-dimensional discrimination'' or ``multi-dimensional fairness'' problem. While well-elaborated in legal literature, the multi-dimensionality of discrimination is less explored in the machine learning community. Recent approaches in this direction mainly follow the so-called intersectional fairness definition from the legal domain, whereas other notions like additive and sequential discrimination are less studied or not considered thus far. In this work, we overview the different definitions of multi-dimensional discrimination/fairness in the legal domain as well as how they have been transferred/ operationalized (if) in the fairness-aware machine learning domain. By juxtaposing these two domains, we draw the connections, identify the limitations, and point out open research directions.

Tai Le Quy, Gunnar Friege, Eirini Ntoutsi

Ensuring fairness is essential for every education system. Machine learning is increasingly supporting the education system and educational data science (EDS) domain, from decision support to educational activities and learning analytics. However, the machine learning-based decisions can be biased because the algorithms may generate the results based on students' protected attributes such as race or gender. Clustering is an important machine learning technique to explore student data in order to support the decision-maker, as well as support educational activities, such as group assignments. Therefore, ensuring high-quality clustering models along with satisfying fairness constraints are important requirements. This chapter comprehensively surveys clustering models and their fairness in EDS. We especially focus on investigating the fair clustering models applied in educational activities. These models are believed to be practical tools for analyzing students' data and ensuring fairness in EDS.

Tai Le Quy, Thi Huyen Nguyen, Gunnar Friege et al.

Predicting students' academic performance is one of the key tasks of educational data mining (EDM). Traditionally, the high forecasting quality of such models was deemed critical. More recently, the issues of fairness and discrimination w.r.t. protected attributes, such as gender or race, have gained attention. Although there are several fairness-aware learning approaches in EDM, a comparative evaluation of these measures is still missing. In this paper, we evaluate different group fairness measures for student performance prediction problems on various educational datasets and fairness-aware learning models. Our study shows that the choice of the fairness measure is important, likewise for the choice of the grade threshold.

Vasilis Gkolemis, Theodore Dalamagas, Eirini Ntoutsi et al.

Accumulated Local Effects (ALE) is a widely-used explainability method for isolating the average effect of a feature on the output, because it handles cases with correlated features well. However, it has two limitations. First, it does not quantify the deviation of instance-level (local) effects from the average (global) effect, known as heterogeneity. Second, for estimating the average effect, it partitions the feature domain into user-defined, fixed-sized bins, where different bin sizes may lead to inconsistent ALE estimations. To address these limitations, we propose Robust and Heterogeneity-aware ALE (RHALE). RHALE quantifies the heterogeneity by considering the standard deviation of the local effects and automatically determines an optimal variable-size bin-splitting. In this paper, we prove that to achieve an unbiased approximation of the standard deviation of local effects within each bin, bin splitting must follow a set of sufficient conditions. Based on these conditions, we propose an algorithm that automatically determines the optimal partitioning, balancing the estimation bias and variance. Through evaluations on synthetic and real datasets, we demonstrate the superiority of RHALE compared to other methods, including the advantages of automatic bin splitting, especially in cases with correlated features.

Arjun Roy, Eirini Ntoutsi

Fairness-aware learning mainly focuses on single task learning (STL). The fairness implications of multi-task learning (MTL) have only recently been considered and a seminal approach has been proposed that considers the fairness-accuracy trade-off for each task and the performance trade-off among different tasks. Instead of a rigid fairness-accuracy trade-off formulation, we propose a flexible approach that learns how to be fair in a MTL setting by selecting which objective (accuracy or fairness) to optimize at each step. We introduce the L2T-FMT algorithm that is a teacher-student network trained collaboratively; the student learns to solve the fair MTL problem while the teacher instructs the student to learn from either accuracy or fairness, depending on what is harder to learn for each task. Moreover, this dynamic selection of which objective to use at each step for each task reduces the number of trade-off weights from 2T to T, where T is the number of tasks. Our experiments on three real datasets show that L2T-FMT improves on both fairness (12-19%) and accuracy (up to 2%) over state-of-the-art approaches.

Yi Cai, Arthur Zimek, Eirini Ntoutsi et al.

The importance of neighborhood construction in local explanation methods has been already highlighted in the literature. And several attempts have been made to improve neighborhood quality for high-dimensional data, for example, texts, by adopting generative models. Although the generators produce more realistic samples, the intuitive sampling approaches in the existing solutions leave the latent space underexplored. To overcome this problem, our work, focusing on local model-agnostic explanations for text classifiers, proposes a progressive approximation approach that refines the neighborhood of a to-be-explained decision with a careful two-stage interpolation using counterfactuals as landmarks. We explicitly specify the two properties that should be satisfied by generative models, the reconstruction ability and the locality-preserving property, to guide the selection of generators for local explanation methods. Moreover, noticing the opacity of generative models during the study, we propose another method that implements progressive neighborhood approximation with probability-based editions as an alternative to the generator-based solution. The explanation results from both methods consist of word-level and instance-level explanations benefiting from the realistic neighborhood. Through exhaustive experiments, we qualitatively and quantitatively demonstrate the effectiveness of the two proposed methods.

Arjun Roy, Christos Koutlis, Symeon Papadopoulos et al.

The generalisation capacity of Multi-Task Learning (MTL) suffers when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients. This is known as negative transfer and leads to a drop in MTL accuracy compared to single-task learning (STL). Lately, there has been a growing focus on the fairness of MTL models, requiring the optimization of both accuracy and fairness for individual tasks. Analogously to negative transfer for accuracy, task-specific fairness considerations might adversely affect the fairness of other tasks when there is a conflict of fairness loss gradients between the jointly learned tasks - we refer to this as Bias Transfer. To address both negative- and bias-transfer in MTL, we propose a novel method called FairBranch, which branches the MTL model by assessing the similarity of learned parameters, thereby grouping related tasks to alleviate negative transfer. Moreover, it incorporates fairness loss gradient conflict correction between adjoining task-group branches to address bias transfer within these task groups. Our experiments on tabular and visual MTL problems show that FairBranch outperforms state-of-the-art MTLs on both fairness and accuracy.

Vasilis Gkolemis, Anargiros Tzerefos, Theodore Dalamagas et al.

Generalized Additive Models (GAMs) are widely used explainable-by-design models in various applications. GAMs assume that the output can be represented as a sum of univariate functions, referred to as components. However, this assumption fails in ML problems where the output depends on multiple features simultaneously. In these cases, GAMs fail to capture the interaction terms of the underlying function, leading to subpar accuracy. To (partially) address this issue, we propose Regionally Additive Models (RAMs), a novel class of explainable-by-design models. RAMs identify subregions within the feature space where interactions are minimized. Within these regions, it is more accurate to express the output as a sum of univariate functions (components). Consequently, RAMs fit one component per subregion of each feature instead of one component per feature. This approach yields a more expressive model compared to GAMs while retaining interpretability. The RAM framework consists of three steps. Firstly, we train a black-box model. Secondly, using Regional Effect Plots, we identify subregions where the black-box model exhibits near-local additivity. Lastly, we fit a GAM component for each identified subregion. We validate the effectiveness of RAMs through experiments on both synthetic and real-world datasets. The results confirm that RAMs offer improved expressiveness compared to GAMs while maintaining interpretability.

Siamak Ghodsi, Harith Alani, Eirini Ntoutsi

With the ever growing involvement of data-driven AI-based decision making technologies in our daily social lives, the fairness of these systems is becoming a crucial phenomenon. However, an important and often challenging aspect in utilizing such systems is to distinguish validity for the range of their application especially under distribution shifts, i.e., when a model is deployed on data with different distribution than the training set. In this paper, we present a case study on the newly released American Census datasets, a reconstruction of the popular Adult dataset, to illustrate the importance of context for fairness and show how remarkably can spatial distribution shifts affect predictive- and fairness-related performance of a model. The problem persists for fairness-aware learning models with the effects of context-specific fairness interventions differing across the states and different population groups. Our study suggests that robustness to distribution shifts is necessary before deploying a model to another context.

Siamak Ghodsi, Eirini Ntoutsi

Group imbalance, resulting from inadequate or unrepresentative data collection methods, is a primary cause of representation bias in datasets. Representation bias can exist with respect to different groups of one or more protected attributes and might lead to prejudicial and discriminatory outcomes toward certain groups of individuals; in cases where a learning model is trained on such biased data. This paper presents MASC, a data augmentation approach that leverages affinity clustering to balance the representation of non-protected and protected groups of a target dataset by utilizing instances of the same protected attributes from similar datasets that are categorized in the same cluster as the target dataset by sharing instances of the protected attribute. The proposed method involves constructing an affinity matrix by quantifying distribution discrepancies between dataset pairs and transforming them into a symmetric pairwise similarity matrix. A non-parametric spectral clustering is then applied to this affinity matrix, automatically categorizing the datasets into an optimal number of clusters. We perform a step-by-step experiment as a demo of our method to show the procedure of the proposed data augmentation method and evaluate and discuss its performance. A comparison with other data augmentation methods, both pre- and post-augmentation, is conducted, along with a model evaluation analysis of each method. Our method can handle non-binary protected attributes so, in our experiments, bias is measured in a non-binary protected attribute setup w.r.t. racial groups distribution for two separate minority groups in comparison with the majority group before and after debiasing. Empirical results imply that our method of augmenting dataset biases using real (genuine) data from similar contexts can effectively debias the target datasets comparably to existing data augmentation strategies.

Chethan Krishnamurthy Ramanaik, Arjun Roy, Eirini Ntoutsi

Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Variational Autoencoders (VAEs), with their probabilistic approach to disentangling latent spaces, show stronger resistance to such perturbations compared to deterministic AEs; however, their resilience against adversarial inputs is still a concern. This study evaluates the robustness of VAEs against non-targeted adversarial attacks by optimizing minimal sample-specific perturbations to cause maximal damage across diverse demographic subgroups (combinations of age and gender). We investigate two questions: whether there are robustness disparities among subgroups, and what factors contribute to these disparities, such as data scarcity and representation entanglement. Our findings reveal that robustness disparities exist but are not always correlated with the size of the subgroup. By using downstream gender and age classifiers and examining latent embeddings, we highlight the vulnerability of subgroups like older women, who are prone to misclassification due to adversarial perturbations pushing their representations toward those of other subgroups.

Tai Le Quy, Gunnar Friege, Eirini Ntoutsi

Group work is a prevalent activity in educational settings, where students are often divided into topic-specific groups based on their preferences. The grouping should reflect the students' aspirations as much as possible. Usually, the resulting groups should also be balanced in terms of protected attributes like gender or race since studies indicate that students might learn better in a diverse group. Moreover, balancing the group cardinalities is also an essential requirement for fair workload distribution across the groups. In this paper, we introduce the multi-fair capacitated (MFC) grouping problem that fairly partitions students into non-overlapping groups while ensuring balanced group cardinalities (with a lower bound and an upper bound), and maximizing the diversity of members in terms of protected attributes. We propose two approaches: a heuristic method and a knapsack-based method to obtain the MFC grouping. The experiments on a real dataset and a semi-synthetic dataset show that our proposed methods can satisfy students' preferences well and deliver balanced and diverse groups regarding cardinality and the protected attribute, respectively.

Emmanouil Panagiotou, Arjun Roy, Eirini Ntoutsi

Due to their data-driven nature, Machine Learning (ML) models are susceptible to bias inherited from data, especially in classification problems where class and group imbalances are prevalent. Class imbalance (in the classification target) and group imbalance (in protected attributes like sex or race) can undermine both ML utility and fairness. Although class and group imbalances commonly coincide in real-world tabular datasets, limited methods address this scenario. While most methods use oversampling techniques, like interpolation, to mitigate imbalances, recent advancements in synthetic tabular data generation offer promise but have not been adequately explored for this purpose. To this end, this paper conducts a comparative analysis to address class and group imbalances using state-of-the-art models for synthetic tabular data generation and various sampling strategies. Experimental results on four datasets, demonstrate the effectiveness of generative models for bias mitigation, creating opportunities for further exploration in this direction.

Vasilis Gkolemis, Christos Diou, Dimitris Kyriakopoulos et al.

Effector is a Python package for interpreting machine learning (ML) models that are trained on tabular data through global and regional feature effects. Global effects, like Partial Dependence Plot (PDP) and Accumulated Local Effects (ALE), are widely used for explaining tabular ML models due to their simplicity -- each feature's average influence on the prediction is summarized by a single 1D plot. However, when features are interacting, global effects can be misleading. Regional effects address this by partitioning the input space into disjoint subregions with minimal interactions within each and computing a separate regional effect per subspace. Regional effects are then visualized by a set of 1D plots per feature. Effector provides efficient implementations of state-of-the-art global and regional feature effects methods under a unified API. The package integrates seamlessly with major ML libraries like scikit-learn and PyTorch. It is designed to be modular and extensible, and comes with comprehensive documentation and tutorials. Effector is an open-source project publicly available on Github at https://github.com/givasile/effector.

Alaa Elobaid, Nathan Ramoly, Lara Younes et al.

Biometric Verification (BV) systems often exhibit accuracy disparities across different demographic groups, leading to biases in BV applications. Assessing and quantifying these biases is essential for ensuring the fairness of BV systems. However, existing bias evaluation metrics in BV have limitations, such as focusing exclusively on match or non-match error rates, overlooking bias on demographic groups with performance levels falling between the best and worst performance levels, and neglecting the magnitude of the bias present. This paper presents an in-depth analysis of the limitations of current bias evaluation metrics in BV and, through experimental analysis, demonstrates their contextual suitability, merits, and limitations. Additionally, it introduces a novel general-purpose bias evaluation measure for BV, the ``Sum of Group Error Differences (SEDG)''. Our experimental results on controlled synthetic datasets demonstrate the effectiveness of demographic bias quantification when using existing metrics and our own proposed measure. We discuss the applicability of the bias evaluation metrics in a set of simulated demographic bias scenarios and provide scenario-based metric recommendations. Our code is publicly available under \url{https://github.com/alaaobeid/SEDG}.

Swati Swati, Arjun Roy, Emmanouil Panagiotou et al.

Fairness-aware classification requires balancing performance and fairness, often intensified by intersectional biases. Conflicting fairness definitions further complicate the task, making it difficult to identify universally fair solutions. Despite growing regulatory and societal demands for equitable AI, popular toolkits offer limited support for exploring multi-dimensional fairness and related trade-offs. To address this, we present mmm-fair, an open-source toolkit leveraging boosting-based ensemble approaches that dynamically optimizes model weights to jointly minimize classification errors and diverse fairness violations, enabling flexible multi-objective optimization. The system empowers users to deploy models that align with their context-specific needs while reliably uncovering intersectional biases often missed by state-of-the-art methods. In a nutshell, mmm-fair uniquely combines in-depth multi-attribute fairness, multi-objective optimization, a no-code, chat-based interface, LLM-powered explanations, interactive Pareto exploration for model selection, custom fairness constraint definition, and deployment-ready models in a single open-source toolkit, a combination rarely found in existing fairness tools. Demo walkthrough available at: https://youtu.be/_rcpjlXFqkw.

Siamak Ghodsi, Amjad Seyedi, Tai Le Quy et al.

Fair graph clustering seeks partitions that respect network structure while maintaining proportional representation across sensitive groups, with applications spanning community detection, team formation, resource allocation, and social network analysis. Many existing approaches enforce rigid constraints or rely on multi-stage pipelines (e.g., spectral embedding followed by $k$-means), limiting trade-off control, interpretability, and scalability. We introduce \emph{DFNMF}, an end-to-end deep nonnegative tri-factorization tailored to graphs that directly optimizes cluster assignments with a soft statistical-parity regularizer. A single parameter $λ$ tunes the fairness--utility balance, while nonnegativity yields parts-based factors and transparent soft memberships. The optimization uses sparse-friendly alternating updates and scales near-linearly with the number of edges. Across synthetic and real networks, DFNMF achieves substantially higher group balance at comparable modularity, often dominating state-of-the-art baselines on the Pareto front. The code is available at https://github.com/SiamakGhodsi/DFNMF.git.

Swati Swati, Arjun Roy, Eirini Ntoutsi

Despite the large body of work on fairness-aware learning for individual modalities like tabular data, images, and text, less work has been done on multimodal data, which fuses various modalities for a comprehensive analysis. In this work, we investigate the fairness and bias implications of multimodal fusion techniques in the context of multimodal AI-based recruitment systems using the FairCVdb dataset. Our results show that early-fusion closely matches the ground truth for both demographics, achieving the lowest MAEs by integrating each modality's unique characteristics. In contrast, late-fusion leads to highly generalized mean scores and higher MAEs. Our findings emphasise the significant potential of early-fusion for accurate and fair applications, even in the presence of demographic biases, compared to late-fusion. Future research could explore alternative fusion strategies and incorporate modality-related fairness constraints to improve fairness. For code and additional insights, visit: https://github.com/Swati17293/Multimodal-AI-Based-Recruitment-FairCVdb

Xuejiao Tang, Wenbin Zhang, Yi Yu et al.

While image understanding on recognition-level has achieved remarkable advancements, reliable visual scene understanding requires comprehensive image understanding on recognition-level but also cognition-level, which calls for exploiting the multi-source information as well as learning different levels of understanding and extensive commonsense knowledge. In this paper, we propose a novel Cognitive Attention Network (CAN) for visual commonsense reasoning to achieve interpretable visual understanding. Specifically, we first introduce an image-text fusion module to fuse information from images and text collectively. Second, a novel inference module is designed to encode commonsense among image, query and response. Extensive experiments on large-scale Visual Commonsense Reasoning (VCR) benchmark dataset demonstrate the effectiveness of our approach. The implementation is publicly available at https://github.com/tanjatang/CAN

Siamak Ghodsi, Seyed Amjad Seyedi, Eirini Ntoutsi

Conventional fair graph clustering methods face two primary challenges: i) They prioritize balanced clusters at the expense of cluster cohesion by imposing rigid constraints, ii) Existing methods of both individual and group-level fairness in graph partitioning mostly rely on eigen decompositions and thus, generally lack interpretability. To address these issues, we propose iFairNMTF, an individual Fairness Nonnegative Matrix Tri-Factorization model with contrastive fairness regularization that achieves balanced and cohesive clusters. By introducing fairness regularization, our model allows for customizable accuracy-fairness trade-offs, thereby enhancing user autonomy without compromising the interpretability provided by nonnegative matrix tri-factorization. Experimental evaluations on real and synthetic datasets demonstrate the superior flexibility of iFairNMTF in achieving fairness and clustering performance.

Ziqi Xu, Sevvandi Kandanaarachchi, Cheng Soon Ong et al.

Item Response Theory (IRT) has been widely used in educational psychometrics to assess student ability, as well as the difficulty and discrimination of test questions. In this context, discrimination specifically refers to how effectively a question distinguishes between students of different ability levels, and it does not carry any connotation related to fairness. In recent years, IRT has been successfully used to evaluate the predictive performance of Machine Learning (ML) models, but this paper marks its first application in fairness evaluation. In this paper, we propose a novel Fair-IRT framework to evaluate a set of predictive models on a set of individuals, while simultaneously eliciting specific parameters, namely, the ability to make fair predictions (a feature of predictive models), as well as the discrimination and difficulty of individuals that affect the prediction results. Furthermore, we conduct a series of experiments to comprehensively understand the implications of these parameters for fairness evaluation. Detailed explanations for item characteristic curves (ICCs) are provided for particular individuals. We propose the flatness of ICCs to disentangle the unfairness between individuals and predictive models. The experiments demonstrate the effectiveness of this framework as a fairness evaluation tool. Two real-world case studies illustrate its potential application in evaluating fairness in both classification and regression tasks. Our paper aligns well with the Responsible Web track by proposing a Fair-IRT framework to evaluate fairness in ML models, which directly contributes to the development of a more inclusive, equitable, and trustworthy AI.

Emmanouil Panagiotou, Manuel Heurich, Tim Landgraf et al.

In the field of Explainable AI (XAI), counterfactual (CF) explanations are one prominent method to interpret a black-box model by suggesting changes to the input that would alter a prediction. In real-world applications, the input is predominantly in tabular form and comprised of mixed data types and complex feature interdependencies. These unique data characteristics are difficult to model, and we empirically show that they lead to bias towards specific feature types when generating CFs. To overcome this issue, we introduce TABCF, a CF explanation method that leverages a transformer-based Variational Autoencoder (VAE) tailored for modeling tabular data. Our approach uses transformers to learn a continuous latent space and a novel Gumbel-Softmax detokenizer that enables precise categorical reconstruction while preserving end-to-end differentiability. Extensive quantitative evaluation on five financial datasets demonstrates that TABCF does not exhibit bias toward specific feature types, and outperforms existing methods in producing effective CFs that align with common CF desiderata.

Vivek Kumar, Eirini Ntoutsi, Pushpraj Singh Rajawat et al.

Large language models (LLMs) have shown promising capabilities in healthcare analysis but face several challenges like hallucinations, parroting, and bias manifestation. These challenges are exacerbated in complex, sensitive, and low-resource domains. Therefore, in this work we introduce IC-AnnoMI, an expert-annotated motivational interviewing (MI) dataset built upon AnnoMI by generating in-context conversational dialogues leveraging LLMs, particularly ChatGPT. IC-AnnoMI employs targeted prompts accurately engineered through cues and tailored information, taking into account therapy style (empathy, reflection), contextual relevance, and false semantic change. Subsequently, the dialogues are annotated by experts, strictly adhering to the Motivational Interviewing Skills Code (MISC), focusing on both the psychological and linguistic dimensions of MI dialogues. We comprehensively evaluate the IC-AnnoMI dataset and ChatGPT's emotional reasoning ability and understanding of domain intricacies by modeling novel classification tasks employing several classical machine learning and current state-of-the-art transformer approaches. Finally, we discuss the effects of progressive prompting strategies and the impact of augmented data in mitigating the biases manifested in IC-AnnoM. Our contributions provide the MI community with not only a comprehensive dataset but also valuable insights for using LLMs in empathetic text generation for conversational therapy in supervised settings.

Herve Debar, Sven Dietrich, Pavel Laskov et al.

Large language models (LLMs) have achieved record adoption in a short period of time across many different sectors including high importance areas such as education [4] and healthcare [23]. LLMs are open-ended models trained on diverse data without being tailored for specific downstream tasks, enabling broad applicability across various domains. They are commonly used for text generation, but also widely used to assist with code generation [3], and even analysis of security information, as Microsoft Security Copilot demonstrates [18]. Traditional Machine Learning (ML) models are vulnerable to adversarial attacks [9]. So the concerns on the potential security implications of such wide scale adoption of LLMs have led to the creation of this working group on the security of LLMs. During the Dagstuhl seminar on "Network Attack Detection and Defense - AI-Powered Threats and Responses", the working group discussions focused on the vulnerability of LLMs to adversarial attacks, rather than their potential use in generating malware or enabling cyberattacks. Although we note the potential threat represented by the latter, the role of the LLMs in such uses is mostly as an accelerator for development, similar to what it is in benign use. To make the analysis more specific, the working group employed ChatGPT as a concrete example of an LLM and addressed the following points, which also form the structure of this report: 1. How do LLMs differ in vulnerabilities from traditional ML models? 2. What are the attack objectives in LLMs? 3. How complex it is to assess the risks posed by the vulnerabilities of LLMs? 4. What is the supply chain in LLMs, how data flow in and out of systems and what are the security implications? We conclude with an overview of open challenges and outlook.

Vasiliki Papanikou, Danae Pla Karidi, Evaggelia Pitoura et al.

As Artificial Intelligence (AI) is increasingly used in areas that significantly impact human lives, concerns about fairness and transparency have grown, especially regarding their impact on protected groups. Recently, the intersection of explainability and fairness has emerged as an important area to promote responsible AI systems. This paper explores how explainability methods can be leveraged to detect and interpret unfairness. We propose a pipeline that integrates local post-hoc explanation methods to derive fairness-related insights. During the pipeline design, we identify and address critical questions arising from the use of explanations as bias detectors such as the relationship between distributive and procedural fairness, the effect of removing the protected attribute, the consistency and quality of results across different explanation methods, the impact of various aggregation strategies of local explanations on group fairness evaluations, and the overall trustworthiness of explanations as bias detectors. Our results show the potential of explanation methods used for fairness while highlighting the need to carefully consider the aforementioned critical aspects.

Vivek Kumar, Pushpraj Singh Rajawat, Eirini Ntoutsi

Recent advancements in large language models (LLMs) have shown their potential across both general and domain-specific tasks. However, there is a growing concern regarding their lack of sensitivity, factual incorrectness in responses, inconsistent expressions of empathy, bias, hallucinations, and overall inability to capture the depth and complexity of human understanding, especially in low-resource and sensitive domains such as psychology. To address these challenges, our study employs a mixed-methods approach to evaluate the efficacy of LLMs in psychotherapy. We use LLMs to generate precise summaries of motivational interviewing (MI) dialogues and design a two-stage annotation scheme based on key components of the Motivational Interviewing Treatment Integrity (MITI) framework, namely evocation, collaboration, autonomy, direction, empathy, and a non-judgmental attitude. Using expert-annotated MI dialogues as ground truth, we formulate multi-class classification tasks to assess model performance under progressive prompting techniques, incorporating one-shot and few-shot prompting. Our results offer insights into LLMs' capacity for understanding complex psychological constructs and highlight best practices to mitigate ``semantic drift" in therapeutic settings. Our work contributes not only to the MI community by providing a high-quality annotated dataset to address data scarcity in low-resource domains but also critical insights for using LLMs for precise contextual interpretation in complex behavioral therapy.

Emmanouil Panagiotou, Benoît Ronval, Arjun Roy et al.

Ensuring fairness in machine learning remains a significant challenge, as models often inherit biases from their training data. Generative models have recently emerged as a promising approach to mitigate bias at the data level while preserving utility. However, many rely on deep architectures, despite evidence that simpler models can be highly effective for tabular data. In this work, we introduce TABFAIRGDT, a novel method for generating fair synthetic tabular data using autoregressive decision trees. To enforce fairness, we propose a soft leaf resampling technique that adjusts decision tree outputs to reduce bias while preserving predictive performance. Our approach is non-parametric, effectively capturing complex relationships between mixed feature types, without relying on assumptions about the underlying data distributions. We evaluate TABFAIRGDT on benchmark fairness datasets and demonstrate that it outperforms state-of-the-art (SOTA) deep generative models, achieving better fairness-utility trade-off for downstream tasks, as well as higher synthetic data quality. Moreover, our method is lightweight, highly efficient, and CPU-compatible, requiring no data pre-processing. Remarkably, TABFAIRGDT achieves a 72% average speedup over the fastest SOTA baseline across various dataset sizes, and can generate fair synthetic data for medium-sized datasets (10 features, 10K samples) in just one second on a standard CPU, making it an ideal solution for real-world fairness-sensitive applications.

Tobias Hyrup, Emmanouil Panagiotou, Arjun Roy et al.

As privacy regulations such as the GDPR and HIPAA and responsibility frameworks for artificial intelligence such as the AI Act gain traction, the ethical and responsible use of real-world data faces increasing constraints. Synthetic data generation has emerged as a promising solution to risk-aware data sharing and model development, particularly for tabular datasets that are foundational to sensitive domains such as healthcare. To address both privacy and fairness concerns in this setting, we propose FLIP (Fair Latent Intervention under Privacy guarantees), a transformer-based variational autoencoder augmented with latent diffusion to generate heterogeneous tabular data. Unlike the typical setup in fairness-aware data generation, we assume a task-agnostic setup, not reliant on a fixed, defined downstream task, thus offering broader applicability. To ensure privacy, FLIP employs Rényi differential privacy (RDP) constraints during training and addresses fairness in the input space with RDP-compatible balanced sampling that accounts for group-specific noise levels across multiple sampling rates. In the latent space, we promote fairness by aligning neuron activation patterns across protected groups using Centered Kernel Alignment (CKA), a similarity measure extending the Hilbert-Schmidt Independence Criterion (HSIC). This alignment encourages statistical independence between latent representations and the protected feature. Empirical results demonstrate that FLIP effectively provides significant fairness improvements for task-agnostic fairness and across diverse downstream tasks under differential privacy constraints.

Chethan Krishnamurthy Ramanaik, Arjun Roy, Tobias Callies et al.

Adversarial robustness of deep autoencoders (AEs) remains relatively unexplored, even though their non-invertible nature poses distinct challenges. Existing attack algorithms during the optimization of imperceptible, norm-bounded adversarial perturbations to maximize output damage in AEs, often stop at sub-optimal attacks. We observe that the adversarial loss gradient vanishes when backpropagated through ill-conditioned layers. This issue arises from near-zero singular values in the Jacobians of these layers, which weaken the gradient signal during optimization. We introduce GRILL, a technique that locally restores gradient signals in ill-conditioned layers, enabling more effective norm-bounded attacks. Through extensive experiments on different architectures of popular AEs, under both sample-specific and universal attack setups, and across standard and adaptive attack settings, we show that our method significantly increases the effectiveness of our adversarial attacks, enabling a more rigorous evaluation of AE robustness.

Julia Huuk, Abheek Dhingra, Eirini Ntoutsi et al.

This paper presents an innovative method for predicting shape errors in 5-axis machining using graph neural networks. The graph structure is defined with nodes representing workpiece surface points and edges denoting the neighboring relationships. The dataset encompasses data from a material removal simulation, process data, and post-machining quality information. Experimental results show that the presented approach can generalize the shape error prediction for the investigated workpiece geometry. Moreover, by modelling spatial and temporal connections within the workpiece, the approach handles a low number of labels compared to non-graphical methods such as Support Vector Machines.

Yi Cai, Arthur Zimek, Eirini Ntoutsi et al.

Recent literature highlights the critical role of neighborhood construction in deriving model-agnostic explanations, with a growing trend toward deploying generative models to improve synthetic instance quality, especially for explaining text classifiers. These approaches overcome the challenges in neighborhood construction posed by the unstructured nature of texts, thereby improving the quality of explanations. However, the deployed generators are usually implemented via neural networks and lack inherent explainability, sparking arguments over the transparency of the explanation process itself. To address this limitation while preserving neighborhood quality, this paper introduces a probability-based editing method as an alternative to black-box text generators. This approach generates neighboring texts by implementing manipulations based on in-text contexts. Substituting the generator-based construction process with recursive probability-based editing, the resultant explanation method, XPROB (explainer with probability-based editing), exhibits competitive performance according to the evaluation conducted on two real-world datasets. Additionally, XPROB's fully transparent and more controllable construction process leads to superior stability compared to the generator-based explainers.

Vasileios Iosifidis, Arjun Roy, Eirini Ntoutsi

Data-driven AI systems can lead to discrimination on the basis of protected attributes like gender or race. One reason for this behavior is the encoded societal biases in the training data (e.g., females are underrepresented), which is aggravated in the presence of unbalanced class distributions (e.g., "granted" is the minority class). State-of-the-art fairness-aware machine learning approaches focus on preserving the \emph{overall} classification accuracy while improving fairness. In the presence of class-imbalance, such methods may further aggravate the problem of discrimination by denying an already underrepresented group (e.g., \textit{females}) the fundamental rights of equal social privileges (e.g., equal credit opportunity). To this end, we propose AdaFair, a fairness-aware boosting ensemble that changes the data distribution at each round, taking into account not only the class errors but also the fairness-related performance of the model defined cumulatively based on the partial ensemble. Except for the in-training boosting of the group discriminated over each round, AdaFair directly tackles imbalance during the post-training phase by optimizing the number of ensemble learners for balanced error performance (BER). AdaFair can facilitate different parity-based fairness notions and mitigate effectively discriminatory outcomes. Our experiments show that our approach can achieve parity in terms of statistical parity, equal opportunity, and disparate mistreatment while maintaining good predictive performance for all classes.

Tai Le Quy, Arjun Roy, Vasileios Iosifidis et al.

As decision-making increasingly relies on Machine Learning (ML) and (big) data, the issue of fairness in data-driven Artificial Intelligence (AI) systems is receiving increasing attention from both research and industry. A large variety of fairness-aware machine learning solutions have been proposed which involve fairness-related interventions in the data, learning algorithms and/or model outputs. However, a vital part of proposing new approaches is evaluating them empirically on benchmark datasets that represent realistic and diverse settings. Therefore, in this paper, we overview real-world datasets used for fairness-aware machine learning. We focus on tabular data as the most common data representation for fairness-aware machine learning. We start our analysis by identifying relationships between the different attributes, particularly w.r.t. protected attributes and class attribute, using a Bayesian network. For a deeper understanding of bias in the datasets, we investigate the interesting relationships using exploratory analysis.

Yi Cai, Arthur Zimek, Eirini Ntoutsi

The importance of the neighborhood for training a local surrogate model to approximate the local decision boundary of a black box classifier has been already highlighted in the literature. Several attempts have been made to construct a better neighborhood for high dimensional data, like texts, by using generative autoencoders. However, existing approaches mainly generate neighbors by selecting purely at random from the latent space and struggle under the curse of dimensionality to learn a good local decision boundary. To overcome this problem, we propose a progressive approximation of the neighborhood using counterfactual instances as initial landmarks and a careful 2-stage sampling approach to refine counterfactuals and generate factuals in the neighborhood of the input instance to be explained. Our work focuses on textual data and our explanations consist of both word-level explanations from the original instance (intrinsic) and the neighborhood (extrinsic) and factual- and counterfactual-instances discovered during the neighborhood generation process that further reveal the effect of altering certain parts in the input text. Our experiments on real-world datasets demonstrate that our method outperforms the competitors in terms of usefulness and stability (for the qualitative part) and completeness, compactness and correctness (for the quantitative part).

Vasileios Iosifidis, Wenbin Zhang, Eirini Ntoutsi

Data-driven learning algorithms are employed in many online applications, in which data become available over time, like network monitoring, stock price prediction, job applications, etc. The underlying data distribution might evolve over time calling for model adaptation as new instances arrive and old instances become obsolete. In such dynamic environments, the so-called data streams, fairness-aware learning cannot be considered as a one-off requirement, but rather it should comprise a continual requirement over the stream. Recent fairness-aware stream classifiers ignore the problem of class imbalance, which manifests in many real-life applications, and mitigate discrimination mainly because they "reject" minority instances at large due to their inability to effectively learn all classes. In this work, we propose \ours, an online fairness-aware approach that maintains a valid and fair classifier over the stream. \ours~is an online boosting approach that changes the training distribution in an online fashion by monitoring stream's class imbalance and tweaks its decision boundary to mitigate discriminatory outcomes over the stream. Experiments on 8 real-world and 1 synthetic datasets from different domains with varying class imbalance demonstrate the superiority of our method over state-of-the-art fairness-aware stream approaches with a range (relative) increase [11.2\%-14.2\%] in balanced accuracy, [22.6\%-31.8\%] in gmean, [42.5\%-49.6\%] in recall, [14.3\%-25.7\%] in kappa and [89.4\%-96.6\%] in statistical parity (fairness).

Simone Fabbrizzi, Symeon Papadopoulos, Eirini Ntoutsi et al.

Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can learn and amplify biases within such data. Thus, the problems of understanding and discovering biases are of utmost importance. Yet, there is no comprehensive survey on bias in visual datasets. Hence, this work aims to: i) describe the biases that might manifest in visual datasets; ii) review the literature on methods for bias discovery and quantification in visual datasets; iii) discuss existing attempts to collect bias-aware visual datasets. A key conclusion of our study is that the problem of bias discovery and quantification in visual datasets is still open, and there is room for improvement in terms of both methods and the range of biases that can be addressed. Moreover, there is no such thing as a bias-free dataset, so scientists and practitioners must become aware of the biases in their datasets and make them explicit. To this end, we propose a checklist to spot different types of bias during visual dataset collection.

Arjun Roy, Vasileios Iosifidis, Eirini Ntoutsi

Recent studies showed that datasets used in fairness-aware machine learning for multiple protected attributes (referred to as multi-discrimination hereafter) are often imbalanced. The class-imbalance problem is more severe for the often underrepresented protected group (e.g. female, non-white, etc.) in the critical minority class. Still, existing methods focus only on the overall error-discrimination trade-off, ignoring the imbalance problem, thus amplifying the prevalent bias in the minority classes. Therefore, solutions are needed to solve the combined problem of multi-discrimination and class-imbalance. To this end, we introduce a new fairness measure, Multi-Max Mistreatment (MMM), which considers both (multi-attribute) protected group and class membership of instances to measure discrimination. To solve the combined problem, we propose a boosting approach that incorporates MMM-costs in the distribution update and post-training selects the optimal trade-off among accurate, balanced, and fair solutions. The experimental results show the superiority of our approach against state-of-the-art methods in producing the best balanced performance across groups and classes and the best accuracy for the protected groups in the minority class.

Tai Le Quy, Arjun Roy, Gunnar Friege et al.

Traditionally, clustering algorithms focus on partitioning the data into groups of similar instances. The similarity objective, however, is not sufficient in applications where a fair-representation of the groups in terms of protected attributes like gender or race, is required for each cluster. Moreover, in many applications, to make the clusters useful for the end-user, a balanced cardinality among the clusters is required. Our motivation comes from the education domain where studies indicate that students might learn better in diverse student groups and of course groups of similar cardinality are more practical e.g., for group assignments. To this end, we introduce the fair-capacitated clustering problem that partitions the data into clusters of similar instances while ensuring cluster fairness and balancing cluster cardinalities. We propose a two-step solution to the problem: i) we rely on fairlets to generate minimal sets that satisfy the fair constraint and ii) we propose two approaches, namely hierarchical clustering and partitioning-based clustering, to obtain the fair-capacitated clustering. The hierarchical approach embeds the additional cardinality requirements during the merging step while the partitioning-based one alters the assignment step using a knapsack problem formulation to satisfy the additional requirements. Our experiments on four educational datasets show that our approaches deliver well-balanced clusters in terms of both fairness and cardinality while maintaining a good clustering quality.

Philip Naumann, Eirini Ntoutsi

Counterfactuals have become a popular technique nowadays for interacting with black-box machine learning models and understanding how to change a particular instance to obtain a desired outcome from the model. However, most existing approaches assume instant materialization of these changes, ignoring that they may require effort and a specific order of application. Recently, methods have been proposed that also consider the order in which actions are applied, leading to the so-called sequential counterfactual generation problem. In this work, we propose a model-agnostic method for sequential counterfactual generation. We formulate the task as a multi-objective optimization problem and present a genetic algorithm approach to find optimal sequences of actions leading to the counterfactuals. Our cost model considers not only the direct effect of an action, but also its consequences. Experimental results show that compared to state-of-the-art, our approach generates less costly solutions, is more efficient and provides the user with a diverse set of solutions to choose from.

Tai Le Quy, Sergej Zerr, Eirini Ntoutsi et al.

Data have an important role in evaluating the performance of NILM algorithms. The best performance of NILM algorithms is achieved with high-quality evaluation data. However, many existing real-world data sets come with a low sampling quality, and often with gaps, lacking data for some recording periods. As a result, in such data, NILM algorithms can hardly recognize devices and estimate their power consumption properly. An important step towards improving the performance of these energy disaggregation methods is to improve the quality of the data sets. In this paper, we carry out experiments using several methods to increase the sampling rate of low sampling rate data. Our results show that augmentation of low-frequency data can support the considered NILM algorithms in estimating appliances' consumption with a higher F-score measurement.

Amir Abolfazli, Eirini Ntoutsi

Online class imbalance learning deals with data streams that are affected by both concept drift and class imbalance. Online learning tries to find a trade-off between exploiting previously learned information and incorporating new information into the model. This requires both the incremental update of the model and the ability to unlearn outdated information. The improper use of unlearning, however, can lead to the retroactive interference problem, a phenomenon that occurs when newly learned information interferes with the old information and impedes the recall of previously learned information. The problem becomes more severe when the classes are not equally represented, resulting in the removal of minority information from the model. In this work, we propose the Drift-Aware Multi-Memory Model (DAM3), which addresses the class imbalance problem in online learning for memory-based models. DAM3 mitigates class imbalance by incorporating an imbalance-sensitive drift detector, preserving a balanced representation of classes in the model, and resolving retroactive interference using a working memory that prevents the forgetting of old information. We show through experiments on real-world and synthetic datasets that the proposed method mitigates class imbalance and outperforms the state-of-the-art methods.

Tongxin Hu, Vasileios Iosifidis, Wentong Liao et al.

In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning. Our approach optimizes a multi-objective loss function in which (a) learns a fair representation by suppressing protected attributes (b) maintains the information content by minimizing a reconstruction loss and (c) allows for solving a classification task in a fair manner by minimizing the classification error and respecting the equalized odds-based fairness regularized. Our experiments on a variety of datasets demonstrate that such a joint approach is superior to separate treatment of unfairness in representation learning or supervised learning. Additionally, our regularizers can be adaptively weighted to balance the different components of the loss function, thus allowing for a very general framework for conjoint fair representation learning and decision making.

Vasileios Iosifidis, Besnik Fetahu, Eirini Ntoutsi

Automated decision making based on big data and machine learning (ML) algorithms can result in discriminatory decisions against certain protected groups defined upon personal data like gender, race, sexual orientation etc. Such algorithms designed to discover patterns in big data might not only pick up any encoded societal biases in the training data, but even worse, they might reinforce such biases resulting in more severe discrimination. The majority of thus far proposed fairness-aware machine learning approaches focus solely on the pre-, in- or post-processing steps of the machine learning process, that is, input data, learning algorithms or derived models, respectively. However, the fairness problem cannot be isolated to a single step of the ML process. Rather, discrimination is often a result of complex interactions between big data and algorithms, and therefore, a more holistic approach is required. The proposed FAE (Fairness-Aware Ensemble) framework combines fairness-related interventions at both pre- and postprocessing steps of the data analysis process. In the preprocessing step, we tackle the problems of under-representation of the protected group (group imbalance) and of class-imbalance by generating balanced training samples. In the post-processing step, we tackle the problem of class overlapping by shifting the decision boundary in the direction of fairness.

Vasileios Iosifidis, Eirini Ntoutsi

The widespread use of ML-based decision making in domains with high societal impact such as recidivism, job hiring and loan credit has raised a lot of concerns regarding potential discrimination. In particular, in certain cases it has been observed that ML algorithms can provide different decisions based on sensitive attributes such as gender or race and therefore can lead to discrimination. Although, several fairness-aware ML approaches have been proposed, their focus has been largely on preserving the overall classification accuracy while improving fairness in predictions for both protected and non-protected groups (defined based on the sensitive attribute(s)). The overall accuracy however is not a good indicator of performance in case of class imbalance, as it is biased towards the majority class. As we will see in our experiments, many of the fairness-related datasets suffer from class imbalance and therefore, tackling fairness requires also tackling the imbalance problem. To this end, we propose AdaFair, a fairness-aware classifier based on AdaBoost that further updates the weights of the instances in each boosting round taking into account a cumulative notion of fairness based upon all current ensemble members, while explicitly tackling class-imbalance by optimizing the number of ensemble members for balanced classification error. Our experiments show that our approach can achieve parity in true positive and true negative rates for both protected and non-protected groups, while it significantly outperforms existing fairness-aware methods up to 25% in terms of balanced error.

Wenbin Zhang, Eirini Ntoutsi

Automated data-driven decision-making systems are ubiquitous across a wide spread of online as well as offline services. These systems, depend on sophisticated learning algorithms and available data, to optimize the service function for decision support assistance. However, there is a growing concern about the accountability and fairness of the employed models by the fact that often the available historic data is intrinsically discriminatory, i.e., the proportion of members sharing one or more sensitive attributes is higher than the proportion in the population as a whole when receiving positive classification, which leads to a lack of fairness in decision support system. A number of fairness-aware learning methods have been proposed to handle this concern. However, these methods tackle fairness as a static problem and do not take the evolution of the underlying stream population into consideration. In this paper, we introduce a learning mechanism to design a fair classifier for online stream based decision-making. Our learning model, FAHT (Fairness-Aware Hoeffding Tree), is an extension of the well-known Hoeffding Tree algorithm for decision tree induction over streams, that also accounts for fairness. Our experiments show that our algorithm is able to deal with discrimination in streaming environments, while maintaining a moderate predictive performance over the stream.

Vasileios Iosifidis, Thi Ngoc Han Tran, Eirini Ntoutsi

The wide spread usage of automated data-driven decision support systems has raised a lot of concerns regarding accountability and fairness of the employed models in the absence of human supervision. Existing fairness-aware approaches tackle fairness as a batch learning problem and aim at learning a fair model which can then be applied to future instances of the problem. In many applications, however, the data comes sequentially and its characteristics might evolve with time. In such a setting, it is counter-intuitive to "fix" a (fair) model over the data stream as changes in the data might incur changes in the underlying model therefore, affecting its fairness. In this work, we propose fairness-enhancing interventions that modify the input data so that the outcome of any stream classifier applied to that data will be fair. Experiments on real and synthetic data show that our approach achieves good predictive performance and low discrimination scores over the course of the stream.

Pavlos Fafalios, Vasileios Iosifidis, Kostas Stefanidis et al.

How did the popularity of the Greek Prime Minister evolve in 2015? How did the predominant sentiment about him vary during that period? Were there any controversial sub-periods? What other entities were related to him during these periods? To answer these questions, one needs to analyze archived documents and data about the query entities, such as old news articles or social media archives. In particular, user-generated content posted in social networks, like Twitter and Facebook, can be seen as a comprehensive documentation of our society, and thus meaningful analysis methods over such archived data are of immense value for sociologists, historians and other interested parties who want to study the history and evolution of entities and events. To this end, in this paper we propose an entity-centric approach to analyze social media archives and we define measures that allow studying how entities were reflected in social media in different time periods and under different aspects, like popularity, attitude, controversiality, and connectedness with other entities. A case study using a large Twitter archive of four years illustrates the insights that can be gained by such an entity-centric and multi-aspect analysis.

Pavlos Fafalios, Vasileios Iosifidis, Eirini Ntoutsi et al.

Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.