Research Papers

Counterfactual Explanations (CEs) are an important tool in Algorithmic Recourse for addressing two questions: 1. What are the crucial factors that led to an automated prediction/decision? 2. How can these factors be changed to achieve a more favorable outcome from a user's perspective? Thus, guiding the user's interaction with AI systems by proposing easy-to-understand explanations and easy-to-attain feasible changes is essential for the trustworthy adoption and long-term acceptance of AI systems. In the literature, various methods have been proposed to generate CEs, and different quality measures have been suggested to evaluate these methods. However, the generation of CEs is usually computationally expensive, and the resulting suggestions are unrealistic and thus non-actionable. In this paper, we introduce a new method to generate CEs for a pre-trained binary classifier by first shaping the latent space of an autoencoder to be a mixture of Gaussian distributions. CEs are then generated in latent space by linear interpolation between the query sample and the centroid of the target class. We show that our method maintains the characteristics of the input sample during the counterfactual search. In various experiments, we show that the proposed method is competitive based on different quality measures on image and tabular datasets -- efficiently returns results that are closer to the original data manifold compared to three state-of-the-art methods, which are essential for realistic high-dimensional machine learning applications.

We propose that future AI transparency and accountability regulations are based on an open global standard for exchanging information about AI systems, which allows co-existence of potentially conflicting local regulations. Then, we discuss key components of a lightweight and effective AI transparency and/or accountability regulation. To prevent overregulation, the proposed approach encourages collaboration between regulators and industry to create a scalable and cost-efficient mutually beneficial solution. This includes using automated assessments and benchmarks with results transparently communicated through AI cards in an open AI register to facilitate meaningful public comparisons of competing AI systems. Such AI cards should report standardized measures tailored to the specific high-risk applications of AI systems and could be used for conformity assessments under AI transparency and accountability policies such as the European Union's AI Act.

Hate speech moderation remains a challenging task for social media platforms. Human-AI collaborative systems offer the potential to combine the strengths of humans' reliability and the scalability of machine learning to tackle this issue effectively. While methods for task handover in human-AI collaboration exist that consider the costs of incorrect predictions, insufficient attention has been paid to accurately estimating these costs. In this work, we propose a value-sensitive rejection mechanism that automatically rejects machine decisions for human moderation based on users' value perceptions regarding machine decisions. We conduct a crowdsourced survey study with 160 participants to evaluate their perception of correct and incorrect machine decisions in the domain of hate speech detection, as well as occurrences where the system rejects making a prediction. Here, we introduce Magnitude Estimation, an unbounded scale, as the preferred method for measuring user (dis)agreement with machine decisions. Our results show that Magnitude Estimation can provide a reliable measurement of participants' perception of machine decisions. By integrating user-perceived value into human-AI collaboration, we further show that it can guide us in 1) determining when to accept or reject machine decisions to obtain the optimal total value a model can deliver and 2) selecting better classification models as compared to the more widely used target of model accuracy.

We address the need to generate faithful explanations of "black box" Deep Learning models. Several tests have been proposed to determine aspects of faithfulness of explanation methods, but they lack cross-domain applicability and a rigorous methodology. Hence, we select an existing test that is model agnostic and is well-suited for comparing one aspect of faithfulness (i.e., sensitivity) of multiple explanation methods, and extend it by specifying formal thresh-olds and building criteria to determine the over-all sensitivity of the explanation method. We present examples of how multiple explanation methods for Convolutional Neural Networks can be compared using this extended methodology. Finally, we discuss the relationship between sensitivity and faithfulness and consider how the test can be adapted to assess different explanation methods in other domains.

B2B sales requires effective prediction of customer growth, identification of upsell potential, and mitigation of churn risks. LinkedIn sales representatives traditionally relied on intuition and fragmented data signals to assess customer performance. This resulted in significant time investment in data understanding as well as strategy formulation and under-investment in active selling. To overcome this challenge, we developed a data product called Account Prioritizer, an intelligent sales account prioritization engine. It uses machine learning recommendation models and integrated account-level explanation algorithms within the sales CRM to automate the manual process of sales book prioritization. A successful A/B test demonstrated that the Account Prioritizer generated a substantial +8.08% increase in renewal bookings for the LinkedIn Business.

Intelligence is a difficult concept to define, despite many attempts at doing so. Rather than trying to settle on a single definition, this article introduces a broad perspective on what intelligence is, by laying out a cascade of definitions that induces both a nested hierarchy of three levels of intelligence and a wider-ranging space that is built around them and approximations to them. Within this intelligence space, regions are identified that correspond to both natural -- most particularly, human -- intelligence and artificial intelligence (AI), along with the crossover notion of humanlike intelligence. These definitions are then exploited in early explorations of four more advanced, and likely more controversial, topics: the singularity, generative AI, ethics, and intellectual property.

A key drawback to using a Open Source third-party library is the risk of introducing malicious attacks. In recently times, these threats have taken a new form, when maintainers turn their Open Source libraries into protestware. This is defined as software containing political messages delivered through these libraries, which can either be malicious or benign. Since developers are willing to freely open-up their software to these libraries, much trust and responsibility are placed on the maintainers to ensure that the library does what it promises to do. Using different frameworks commonly used in AI ethics, we illustrate how an open-source maintainer's decision to protest is influenced by different stakeholders (viz., their membership in the OSS community, their personal views, financial motivations, social status, and moral viewpoints), making protestware a multifaceted and intricate matter.

Is the rapid adoption of Artificial Intelligence a sign that creative destruction (a capitalist innovation process first theorised in 1942) is occurring? Although its theory suggests that it is only visible over time in aggregate, this paper devises three hypotheses to test its presence on a macro level and research methods to produce the required data. This paper tests the theory using news archives, questionnaires, and interviews with industry professionals. It considers the risks of adopting Artificial Intelligence, its current performance in the market and its general applicability to the role. The results suggest that creative destruction is occurring in the AML industry despite the activities of the regulators acting as natural blockers to innovation. This is a pressurised situation where current-generation Artificial Intelligence may offer more harm than benefit. For managers, this papers results suggest that safely pursuing AI in AML requires having realistic expectations of Artificial Intelligence's benefits combined with using a framework for AI Ethics.

Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model in the form of local linear explanations. With such information, the user can judge which features are locally relevant for the classification outcome, and get an understanding of how the model reasons. Standard supervised learning processes are purely driven by the original features and target labels, without any feedback loop informed by the local relevance of the features identified by the post-hoc explanations. In this paper, we exploit this newly obtained information to design a feature engineering phase, where we combine explanations with feature values. To do so, we develop two different strategies, named Iterative Dataset Weighting and Targeted Replacement Values, which generate streamlined models that better mimic the explanation process presented to the user. We show how these streamlined models compare to the original black-box classifiers, in terms of accuracy and compactness of the newly produced explanations.

This paper proposes an alternative approach to the basic taxonomy of explanations produced by explainable artificial intelligence techniques. Methods of Explainable Artificial Intelligence (XAI) were developed to answer the question why a certain prediction or estimation was made, preferably in terms easy to understand by the human agent. XAI taxonomies proposed in the literature mainly concentrate their attention on distinguishing explanations with respect to involving the human agent, which makes it complicated to provide a more mathematical approach to distinguish and compare different explanations. This paper narrows its attention to the cases where the data set of interest belongs to $\mathbb{R} ^n$ and proposes a simple linear algebra-based taxonomy for local explanations.

In modern business processes, the amount of data collected has increased substantially in recent years. Because this data can potentially yield valuable insights, automated knowledge extraction based on process mining has been proposed, among other techniques, to provide users with intuitive access to the information contained therein. At present, the majority of technologies aim to reconstruct explicit business process models. These are directly interpretable but limited concerning the integration of diverse and real-valued information sources. On the other hand, Machine Learning (ML) benefits from the vast amount of data available and can deal with high-dimensional sources, yet it has rarely been applied to being used in processes. In this contribution, we evaluate the capability of modern Transformer architectures as well as more classical ML technologies of modeling process regularities, as can be quantitatively evaluated by their prediction capability. In addition, we demonstrate the capability of attentional properties and feature relevance determination by highlighting features that are crucial to the processes' predictive abilities. We demonstrate the efficacy of our approach using five benchmark datasets and show that the ML models are capable of predicting critical outcomes and that the attention mechanisms or XAI components offer new insights into the underlying processes.

Many visualization techniques have been created to explain the behavior of computer vision models, but they largely consist of static diagrams that convey limited information. Interactive visualizations allow users to more easily interpret a model's behavior, but most are not easily reusable for new models. We introduce Visual Feature Search, a novel interactive visualization that is adaptable to any CNN and can easily be incorporated into a researcher's workflow. Our tool allows a user to highlight an image region and search for images from a given dataset with the most similar model features. We demonstrate how our tool elucidates different aspects of model behavior by performing experiments on a range of applications, such as in medical imaging and wildlife classification.