Research Papers

TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE

Emmanouil Panagiotou, Manuel Heurich, Tim Landgraf +1

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.

As Large Language Models (LLMs) become increasingly sophisticated and ubiquitous in natural language processing (NLP) applications, ensuring their robustness, trustworthiness, and alignment with human values has become a critical challenge. This paper presents a novel framework for contextual grounding in textual models, with a particular emphasis on the Context Representation stage. Our approach aims to enhance the reliability and ethical alignment of these models through a comprehensive, context-aware methodology. By explicitly capturing and representing relevant situational, cultural, and ethical contexts in a machine-readable format, we lay the foundation for anchoring a model's behavior within these contexts. Our approach leverages techniques from knowledge representation and reasoning, such as ontologies, semantic web technologies, and logic-based formalisms. We evaluate our framework on real-world textual datasets, demonstrating its effectiveness in improving model performance, fairness, and alignment with human expectations, while maintaining high accuracy. Furthermore, we discuss the other key components of the framework, including context-aware encoding, context-aware learning, interpretability and explainability, and continuous monitoring and adaptation. This research contributes to the growing body of work on responsible AI, offering a practical approach to developing more reliable, trustworthy, and ethically-aligned language models. Our findings have significant implications for the deployment of LLMs in sensitive domains such as healthcare, legal systems, and social services, where contextual understanding is paramount.

AI systems cannot exist without data. Now that AI models (data science and AI) have matured and are readily available to apply in practice, most organizations struggle with the data infrastructure to do so. There is a growing need for data engineers that know how to prepare data for AI systems or that can setup enterprise-wide data architectures for analytical projects. But until now, the data engineering part of AI engineering has not been getting much attention, in favor of discussing the modeling part. In this paper we aim to change this by perform a mapping study on data engineering for AI systems, i.e., AI data engineering. We found 25 relevant papers between January 2019 and June 2023, explaining AI data engineering activities. We identify which life cycle phases are covered, which technical solutions or architectures are proposed and which lessons learned are presented. We end by an overall discussion of the papers with implications for practitioners and researchers. This paper creates an overview of the body of knowledge on data engineering for AI. This overview is useful for practitioners to identify solutions and best practices as well as for researchers to identify gaps.

We identify the task of measuring data to quantitatively characterize the composition of machine learning data and datasets. Similar to an object's height, width, and volume, data measurements quantify different attributes of data along common dimensions that support comparison. Several lines of research have proposed what we refer to as measurements, with differing terminology; we bring some of this work together, particularly in fields of computer vision and language, and build from it to motivate measuring data as a critical component of responsible AI development. Measuring data aids in systematically building and analyzing machine learning (ML) data towards specific goals and gaining better control of what modern ML systems will learn. We conclude with a discussion of the many avenues of future work, the limitations of data measurements, and how to leverage these measurement approaches in research and practice.

Artificial intelligence-empowred Real-Time Bidding (AIRTB) is regarded as one of the most enabling technologies for online advertising. It has attracted significant research attention from diverse fields such as pattern recognition, game theory and mechanism design. Despite of its remarkable development and deployment, the AIRTB system can sometimes harm the interest of its participants (e.g., depleting the advertisers' budget with various kinds of fraud). As such, building trustworthy AIRTB auctioning systems has emerged as an important direction of research in this field in recent years. Due to the highly interdisciplinary nature of this field and a lack of a comprehensive survey, it is a challenge for researchers to enter this field and contribute towards building trustworthy AIRTB technologies. This paper bridges this important gap in trustworthy AIRTB literature. We start by analysing the key concerns of various AIRTB stakeholders and identify three main dimensions of trust building in AIRTB, namely security, robustness and fairness. For each of these dimensions, we propose a unique taxonomy of the state of the art, trace the root causes of possible breakdown of trust, and discuss the necessity of the given dimension. This is followed by a comprehensive review of existing strategies for fulfilling the requirements of each trust dimension. In addition, we discuss the promising future directions of research essential towards building trustworthy AIRTB systems to benefit the field of online advertising.

We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different tasks from 2 relatively diverse datasets. The datasets are diverse in terms of the number and types of tasks they have. To improve performance, we augment the training data by using an autoregressive model. We achieve near-SoTA results on a couple of the tasks - macro F1 scores of 81.66% for task A of the OLID 2019 dataset and 82.54% for task A of the hate speech and offensive content (HASOC) 2021 dataset, where SoTA are 82.9% and 83.05%, respectively. We perform error analysis and explain why one of the models (Bi-LSTM) makes the predictions it does by using a publicly available algorithm: Integrated Gradient (IG). This is because explainable artificial intelligence (XAI) is essential for earning the trust of users. The main contributions of this work are the implementation method of T5, which is discussed; the data augmentation using a new conversational AI model checkpoint, which brought performance improvements; and the revelation on the shortcomings of HASOC 2021 dataset. It reveals the difficulties of poor data annotation by using a small set of examples where the T5 model made the correct predictions, even when the ground truth of the test set were incorrect (in our opinion). We also provide our model checkpoints on the HuggingFace hub1 to foster transparency.

Fairness Implications of Encoding Protected Categorical Attributes

Carlos Mougan, Jose M. Alvarez, Salvatore Ruggieri +1

Past research has demonstrated that the explicit use of protected attributes in machine learning can improve both performance and fairness. Many machine learning algorithms, however, cannot directly process categorical attributes, such as country of birth or ethnicity. Because protected attributes frequently are categorical, they must be encoded as features that can be input to a chosen machine learning algorithm, e.g.\ support vector machines, gradient boosting decision trees or linear models. Thereby, encoding methods influence how and what the machine learning algorithm will learn, affecting model performance and fairness. This work compares the accuracy and fairness implications of the two most well-known encoding methods: \emph{one-hot encoding} and \emph{target encoding}. We distinguish between two types of induced bias that may arise from these encoding methods and may lead to unfair models. The first type, \textit{irreducible bias}, is due to direct group category discrimination, and the second type, \textit{reducible bias}, is due to the large variance in statistically underrepresented groups. We investigate the interaction between categorical encodings and target encoding regularization methods that reduce unfairness. Furthermore, we consider the problem of intersectional unfairness that may arise when machine learning best practices improve performance measures by encoding several categorical attributes into a high-cardinality feature.

Measurement of social phenomena is everywhere, unavoidably, in sociotechnical systems. This is not (only) an academic point: Fairness-related harms emerge when there is a mismatch in the measurement process between the thing we purport to be measuring and the thing we actually measure. However, the measurement process -- where social, cultural, and political values are implicitly encoded in sociotechnical systems -- is almost always obscured. Furthermore, this obscured process is where important governance decisions are encoded: governance about which systems are fair, which individuals belong in which categories, and so on. We can then use the language of measurement, and the tools of construct validity and reliability, to uncover hidden governance decisions. In particular, we highlight two types of construct validity, content validity and consequential validity, that are useful to elicit and characterize the feedback loops between the measurement, social construction, and enforcement of social categories. We then explore the constructs of fairness, robustness, and responsibility in the context of governance in and for responsible AI. Together, these perspectives help us unpack how measurement acts as a hidden governance process in sociotechnical systems. Understanding measurement as governance supports a richer understanding of the governance processes already happening in AI -- responsible or otherwise -- revealing paths to more effective interventions.

This article examines the concept of 'AI fairness' for people with disabilities from the perspective of data protection and equality law. This examination demonstrates that there is a need for a distinctive approach to AI fairness that is fundamentally different to that used for other protected characteristics, due to the different ways in which discrimination and data protection law applies in respect of Disability. We articulate this new agenda for AI fairness for people with disabilities, explaining how combining data protection and equality law creates new opportunities for disabled people's organisations and assistive technology researchers alike to shape the use of AI, as well as to challenge potential harmful uses.

In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contributions. First, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the induced bias prevention quality of pruned models. Second, we demonstrate that knowledge distillation can mitigate induced bias in pruned neural networks, even with unbalanced datasets. Third, we reveal that model similarity has strong correlations with pruning induced bias, which provides a powerful method to explain why bias occurs in pruned neural networks. Our code is available at https://github.com/codestar12/pruning-distilation-bias

How do ethical arguments affect AI adoption in business? We randomly expose business decision-makers to arguments used in AI fairness activism. Arguments emphasizing the inescapability of algorithmic bias lead managers to abandon AI for manual review by humans and report greater expectations about lawsuits and negative PR. These effects persist even when AI lowers gender and racial disparities and when engineering investments to address AI fairness are feasible. Emphasis on status quo comparisons yields opposite effects. We also measure the effects of "scientific veneer" in AI ethics arguments. Scientific veneer changes managerial behavior but does not asymmetrically benefit favorable (versus critical) AI activism.

The increasing development in the consumer credit card market brings substantial regulatory and risk management challenges. The advanced machine learning models applications bring concerns about model transparency and fairness for both financial institutions and regulatory departments. In this study, we evaluate the consistency of one commonly used Explainable AI (XAI) technology, SHAP, for variable explanation in credit card probability of default models via a case study about credit card default prediction. The study shows the consistency is related to the variable importance level and hence provides practical recommendation for credit risk management