Research Papers

A main drawback of eXplainable Artificial Intelligence (XAI) approaches is the feature independence assumption, hindering the study of potential variable dependencies. This leads to approximating black box behaviors by analyzing the effects on randomly generated feature values that may rarely occur in the original samples. This paper addresses this issue by integrating causal knowledge in an XAI method to enhance transparency and enable users to assess the quality of the generated explanations. Specifically, we propose a novel extension to a widely used local and model-agnostic explainer, which encodes explicit causal relationships within the data surrounding the instance being explained. Extensive experiments show that our approach overcomes the original method in terms of faithfully replicating the black-box model's mechanism and the consistency and reliability of the generated explanations.

Human-Center eXplainable AI (HCXAI) literature identifies the need to address user needs. This paper examines how existing XAI research involves human users in designing and developing XAI systems and identifies limitations in current practices, especially regarding how researchers identify user requirements. Finally, we propose several suggestions on how to derive better user requirements.

Deep learning based computer vision models are increasingly used by urban planners to support decision making for shaping urban environments. Such models predict how people perceive the urban environment quality in terms of e.g. its safety or beauty. However, the blackbox nature of deep learning models hampers urban planners to understand what landscape objects contribute to a particularly high quality or low quality urban space perception. This study investigates how computer vision models can be used to extract relevant policy information about peoples' perception of the urban space. To do so, we train two widely used computer vision architectures; a Convolutional Neural Network and a transformer, and apply GradCAM -- a well-known ex-post explainable AI technique -- to highlight the image regions important for the model's prediction. Using these GradCAM visualizations, we manually annotate the objects relevant to the models' perception predictions. As a result, we are able to discover new objects that are not represented in present object detection models used for annotation in previous studies. Moreover, our methodological results suggest that transformer architectures are better suited to be used in combination with GradCAM techniques. Code is available on Github.

Improving Vaccine Stance Detection by Combining Online and Offline Data

Anique Tahir, Lu Cheng, Paras Sheth +1

Differing opinions about COVID-19 have led to various online discourses regarding vaccines. Due to the detrimental effects and the scale of the COVID-19 pandemic, detecting vaccine stance has become especially important and is attracting increasing attention. Communication during the pandemic is typically done via online and offline sources, which provide two complementary avenues for detecting vaccine stance. Therefore, this paper aims to (1) study the importance of integrating online and offline data to vaccine stance detection; and (2) identify the critical online and offline attributes that influence an individual's vaccine stance. We model vaccine hesitancy as a surrogate for identifying the importance of online and offline factors. With the aid of explainable AI and combinatorial analysis, we conclude that both online and offline factors help predict vaccine stance.

On Computing Relevant Features for Explaining NBCs

Yacine Izza, Joao Marques-Silva

Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations. One alternative are the so-called formal approaches to XAI, that include PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. The computation of relevant features serves to trade off probabilistic precision for the number of features in an explanation. However, even for very simple classifiers, the complexity of computing sets of relevant features is prohibitive. This paper investigates the computation of relevant sets for Naive Bayes Classifiers (NBCs), and shows that, in practice, these are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained with NBCs.

The explanation to an AI model's prediction used to support decision making in cyber security, is of critical importance. It is especially so when the model's incorrect prediction can lead to severe damages or even losses to lives and critical assets. However, most existing AI models lack the ability to provide explanations on their prediction results, despite their strong performance in most scenarios. In this work, we propose a novel explainable AI method, called PhilaeX, that provides the heuristic means to identify the optimized subset of features to form the complete explanations of AI models' predictions. It identifies the features that lead to the model's borderline prediction, and those with positive individual contributions are extracted. The feature attributions are then quantified through the optimization of a Ridge regression model. We verify the explanation fidelity through two experiments. First, we assess our method's capability in correctly identifying the activated features in the adversarial samples of Android malwares, through the features attribution values from PhilaeX. Second, the deduction and augmentation tests, are used to assess the fidelity of the explanations. The results show that PhilaeX is able to explain different types of classifiers correctly, with higher fidelity explanations, compared to the state-of-the-arts methods such as LIME and SHAP.

Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate metrics, machine learning algorithms are increasingly being used to improve the efficiency of the process. Explanations help to facilitate communication between the algorithm and the human decision-maker, making it easier for the latter to interpret and make decisions on the basis of predictions by the former. Feature-based explanations' semantics of causal models, however, induce leakage from the decision-maker's prior beliefs. Our findings from a field experiment demonstrate empirically how this leads to confirmation bias and disparate impact on the decision-maker's confidence in the predictions. Such differences can lead to sub-optimal and biased decision outcomes.

Item ranking systems support users in multi-criteria decision-making tasks. Users need to trust rankings and ranking algorithms to reflect user preferences nicely while avoiding systematic errors and biases. However, today only few approaches help end users, model developers, and analysts to explain rankings. We report on the study of explanation approaches from the perspectives of recommender systems, explainable AI, and visualization research and propose the first cross-domain design space for explainers of item rankings. In addition, we leverage the descriptive power of the design space to characterize a) existing explainers and b) three main user groups involved in ranking explanation tasks. The generative power of the design space is a means for future designers and developers to create more target-oriented solutions in this only weakly exploited space.

Argumentative Explanations for Pattern-Based Text Classifiers

Piyawat Lertvittayakumjorn, Francesca Toni

Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this paper, we fill this gap by focusing on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification. We do so because, albeit interpretable, PLR is challenging when it comes to explanations. In particular, we found that a standard way to extract explanations from this model does not consider relations among the features, making the explanations hardly plausible to humans. Hence, we propose AXPLR, a novel explanation method using (forms of) computational argumentation to generate explanations (for outputs computed by PLR) which unearth model agreements and disagreements among the features. Specifically, we use computational argumentation as follows: we see features (patterns) in PLR as arguments in a form of quantified bipolar argumentation frameworks (QBAFs) and extract attacks and supports between arguments based on specificity of the arguments; we understand logistic regression as a gradual semantics for these QBAFs, used to determine the arguments' dialectic strength; and we study standard properties of gradual semantics for QBAFs in the context of our argumentative re-interpretation of PLR, sanctioning its suitability for explanatory purposes. We then show how to extract intuitive explanations (for outputs computed by PLR) from the constructed QBAFs. Finally, we conduct an empirical evaluation and two experiments in the context of human-AI collaboration to demonstrate the advantages of our resulting AXPLR method.

To compare alternative taxi schedules and to compute them, as well as to provide insights into an upcoming taxi trip to drivers and passengers, the duration of a trip or its Estimated Time of Arrival (ETA) is predicted. To reach a high prediction precision, machine learning models for ETA are state of the art. One yet unexploited option to further increase prediction precision is to combine multiple ETA models into an ensemble. While an increase of prediction precision is likely, the main drawback is that the predictions made by such an ensemble become less transparent due to the sophisticated ensemble architecture. One option to remedy this drawback is to apply eXplainable Artificial Intelligence (XAI). The contribution of this paper is three-fold. First, we combine multiple machine learning models from our previous work for ETA into a two-level ensemble model - a stacked ensemble model - which on its own is novel; therefore, we can outperform previous state-of-the-art static route-free ETA approaches. Second, we apply existing XAI methods to explain the first- and second-level models of the ensemble. Third, we propose three joining methods for combining the first-level explanations with the second-level ones. Those joining methods enable us to explain stacked ensembles for regression tasks. An experimental evaluation shows that the ETA models correctly learned the importance of those input features driving the prediction.

This article discusses open problems, implemented solutions, and future research in the area of responsible AI in healthcare. In particular, we illustrate two main research themes related to the work of two laboratories within the Department of Informatics, Systems, and Communication at the University of Milano-Bicocca. The problems addressed concern, in particular, {uncertainty in medical data and machine advice}, and the problem of online health information disorder.

Evaluating a Methodology for Increasing AI Transparency: A Case Study

David Piorkowski, John Richards, Michael Hind

In reaction to growing concerns about the potential harms of artificial intelligence (AI), societies have begun to demand more transparency about how AI models and systems are created and used. To address these concerns, several efforts have proposed documentation templates containing questions to be answered by model developers. These templates provide a useful starting point, but no single template can cover the needs of diverse documentation consumers. It is possible in principle, however, to create a repeatable methodology to generate truly useful documentation. Richards et al. [25] proposed such a methodology for identifying specific documentation needs and creating templates to address those needs. Although this is a promising proposal, it has not been evaluated. This paper presents the first evaluation of this user-centered methodology in practice, reporting on the experiences of a team in the domain of AI for healthcare that adopted it to increase transparency for several AI models. The methodology was found to be usable by developers not trained in user-centered techniques, guiding them to creating a documentation template that addressed the specific needs of their consumers while still being reusable across different models and use cases. Analysis of the benefits and costs of this methodology are reviewed and suggestions for further improvement in both the methodology and supporting tools are summarized.