Research Papers

Effects of Explanation Specificity on Passengers in Autonomous Driving

Daniel Omeiza, Raunak Bhattacharyya, Nick Hawes +2

The nature of explanations provided by an explainable AI algorithm has been a topic of interest in the explainable AI and human-computer interaction community. In this paper, we investigate the effects of natural language explanations' specificity on passengers in autonomous driving. We extended an existing data-driven tree-based explainer algorithm by adding a rule-based option for explanation generation. We generated auditory natural language explanations with different levels of specificity (abstract and specific) and tested these explanations in a within-subject user study (N=39) using an immersive physical driving simulation setup. Our results showed that both abstract and specific explanations had similar positive effects on passengers' perceived safety and the feeling of anxiety. However, the specific explanations influenced the desire of passengers to takeover driving control from the autonomous vehicle (AV), while the abstract explanations did not. We conclude that natural language auditory explanations are useful for passengers in autonomous driving, and their specificity levels could influence how much in-vehicle participants would wish to be in control of the driving activity.

The absence of transparency and explainability hinders the clinical adoption of Machine learning (ML) algorithms. Although various methods of explainable artificial intelligence (XAI) have been suggested, there is a lack of literature that delves into their practicality and assesses them based on criteria that could foster trust in clinical environments. To address this gap this study evaluates two popular XAI methods used for explaining predictive models in the healthcare context in terms of whether they (i) generate domain-appropriate representation, i.e. coherent with respect to the application task, (ii) impact clinical workflow and (iii) are consistent. To that end, explanations generated at the cohort and patient levels were analysed. The paper reports the first benchmarking of the XAI methods applied to risk prediction models obtained by evaluating the concordance between generated explanations and the trigger of a future clinical deterioration episode recorded by the data collection system. We carried out an analysis using two Electronic Medical Records (EMR) datasets sourced from Australian major hospitals. The findings underscore the limitations of state-of-the-art XAI methods in the clinical context and their potential benefits. We discuss these limitations and contribute to the theoretical development of trustworthy XAI solutions where clinical decision support guides the choice of intervention by suggesting the pattern or drivers for clinical deterioration in the future.

Towards Fair and Explainable AI using a Human-Centered AI Approach

Bhavya Ghai

The rise of machine learning (ML) is accompanied by several high-profile cases that have stressed the need for fairness, accountability, explainability and trust in ML systems. The existing literature has largely focused on fully automated ML approaches that try to optimize for some performance metric. However, human-centric measures like fairness, trust, explainability, etc. are subjective in nature, context-dependent, and might not correlate with conventional performance metrics. To deal with these challenges, we explore a human-centered AI approach that empowers people by providing more transparency and human control. In this dissertation, we present 5 research projects that aim to enhance explainability and fairness in classification systems and word embeddings. The first project explores the utility/downsides of introducing local model explanations as interfaces for machine teachers (crowd workers). Our study found that adding explanations supports trust calibration for the resulting ML model and enables rich forms of teaching feedback. The second project presents D-BIAS, a causality-based human-in-the-loop visual tool for identifying and mitigating social biases in tabular datasets. Apart from fairness, we found that our tool also enhances trust and accountability. The third project presents WordBias, a visual interactive tool that helps audit pre-trained static word embeddings for biases against groups, such as females, or subgroups, such as Black Muslim females. The fourth project presents DramatVis Personae, a visual analytics tool that helps identify social biases in creative writing. Finally, the last project presents an empirical study aimed at understanding the cumulative impact of multiple fairness-enhancing interventions at different stages of the ML pipeline on fairness, utility and different population groups. We conclude by discussing some of the future directions.

Experiential AI: A transdisciplinary framework for legibility and agency in AI

Drew Hemment, Dave Murray-Rust, Vaishak Belle +3

Experiential AI is presented as a research agenda in which scientists and artists come together to investigate the entanglements between humans and machines, and an approach to human-machine learning and development where knowledge is created through the transformation of experience. The paper discusses advances and limitations in the field of explainable AI; the contribution the arts can offer to address those limitations; and methods to bring creative practice together with emerging technology to create rich experiences that shed light on novel socio-technical systems, changing the way that publics, scientists and practitioners think about AI.

Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine learning algorithms, and the research regarding the explainability-accuracy tradeoff is still in its infancy especially when we are concerned about complex machine learning techniques like neural networks and deep learning (DL). In this work, we introduce a new approach for complex models based on the co-relation impact which enhances the explainability considerably while also ensuring the accuracy at a high level. We propose approaches for both scenarios of independent features and dependent features. In addition, we study the uncertainty associated with features and output. Furthermore, we provide an upper bound of the computation complexity of our proposed approach for the dependent features. The complexity bound depends on the order of logarithmic of the number of observations which provides a reliable result considering the higher dimension of dependent feature space with a smaller number of observations.

Over the last few years, the number of works about deep learning applied to the medical field has increased enormously. The necessity of a rigorous assessment of these models is required to explain these results to all people involved in medical exams. A recent field in the machine learning area is explainable artificial intelligence, also known as XAI, which targets to explain the results of such black box models to permit the desired assessment. This survey analyses several recent studies in the XAI field applied to medical diagnosis research, allowing some explainability of the machine learning results in several different diseases, such as cancers and COVID-19.

Human-AI decision making is becoming increasingly ubiquitous, and explanations have been proposed to facilitate better Human-AI interactions. Recent research has investigated the positive impact of explanations on decision subjects' fairness perceptions in algorithmic decision-making. Despite these advances, most studies have captured the effect of explanations in isolation, considering explanations as ends in themselves, and reducing them to technical solutions provided through XAI methodologies. In this vision paper, we argue that the effect of explanations on fairness perceptions should rather be captured in relation to decision subjects' right to contest such decisions. Since contestable AI systems are open to human intervention throughout their lifecycle, contestability requires explanations that go beyond outcomes and also capture the rationales that led to the development and deployment of the algorithmic system in the first place. We refer to such explanations as process-centric explanations. In this work, we introduce the notion of process-centric explanations and describe some of the main challenges and research opportunities for generating and evaluating such explanations.

In the field of functional genomics, the analysis of gene expression profiles through Machine and Deep Learning is increasingly providing meaningful insight into a number of diseases. The paper proposes a novel algorithm to perform Feature Selection on genomic-scale data, which exploits the reconstruction capabilities of autoencoders and an ad-hoc defined Explainable Artificial Intelligence-based score in order to select the most informative genes for diagnosis, prognosis, and precision medicine. Results of the application on a Chronic Lymphocytic Leukemia dataset evidence the effectiveness of the algorithm, by identifying and suggesting a set of meaningful genes for further medical investigation.

Deep Learning (DL) is one of the most popular research topics in machine learning and DL-driven image recognition systems have developed rapidly. Recent research has employed metamorphic testing (MT) to detect misclassified images. Most of them discuss metamorphic relations (MR), with limited attention given to which regions should be transformed. We focus on the fact that there are sensitive regions where even small transformations can easily change the prediction results and propose an MT framework that efficiently tests for regions prone to misclassification by transforming these sensitive regions. Our evaluation demonstrated that the sensitive regions can be specified by Explainable AI (XAI) and our framework effectively detects faults.

The applications of Artificial Intelligence (AI) methods especially machine learning techniques have increased in recent years. Classification algorithms have been successfully applied to different problems such as requirement classification. Although these algorithms have good performance, most of them cannot explain how they make a decision. Explainable Artificial Intelligence (XAI) is a set of new techniques that explain the predictions of machine learning algorithms. In this work, the applicability of XAI for software requirement classification is studied. An explainable software requirement classifier is presented using the LIME algorithm. The explainability of the proposed method is studied by applying it to the PROMISE software requirement dataset. The results show that XAI can help the analyst or requirement specifier to better understand why a specific requirement is classified as functional or non-functional. The important keywords for such decisions are identified and analyzed in detail. The experimental study shows that the XAI can be used to help analysts and requirement specifiers to better understand the predictions of the classifiers for categorizing software requirements. Also, the effect of the XAI on feature reduction is analyzed. The results showed that the XAI model has a positive role in feature analysis.

Explainable Artificial Intelligence (XAI) techniques are frequently required by users in many AI systems with the goal of understanding complex models, their associated predictions, and gaining trust. While suitable for some specific tasks during development, their adoption by organisations to enhance trust in machine learning systems has unintended consequences. In this paper we discuss XAI's limitations in deployment and conclude that transparency alongside with rigorous validation are better suited to gaining trust in AI systems.

Decisions such as which movie to watch next, which song to listen to, or which product to buy online, are increasingly influenced by recommender systems and user models that incorporate information on users' past behaviours, preferences, and digitally created content. Machine learning models that enable recommendations and that are trained on user data may unintentionally leverage information on human characteristics that are considered vulnerabilities, such as depression, young age, or gambling addiction. The use of algorithmic decisions based on latent vulnerable state representations could be considered manipulative and could have a deteriorating impact on the condition of vulnerable individuals. In this paper, we are concerned with the problem of machine learning models inadvertently modelling vulnerabilities, and want to raise awareness for this issue to be considered in legislation and AI ethics. Hence, we define and describe common vulnerabilities, and illustrate cases where they are likely to play a role in algorithmic decision-making. We propose a set of requirements for methods to detect the potential for vulnerability modelling, detect whether vulnerable groups are treated differently by a model, and detect whether a model has created an internal representation of vulnerability. We conclude that explainable artificial intelligence methods may be necessary for detecting vulnerability exploitation by machine learning-based recommendation systems.