Research Papers

Categorical Foundations of Explainable AI: A Unifying Theory

Pietro Barbiero, Stefano Fioravanti, Francesco Giannini +3

Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound mathematical formalization of key XAI notions -- remarkably including the term "explanation" which still lacks a precise definition. To bridge this gap, this paper presents the first mathematically rigorous definitions of key XAI notions and processes, using the well-funded formalism of Category theory. We show that our categorical framework allows to: (i) model existing learning schemes and architectures, (ii) formally define the term "explanation", (iii) establish a theoretical basis for XAI taxonomies, and (iv) analyze commonly overlooked aspects of explaining methods. As a consequence, our categorical framework promotes the ethical and secure deployment of AI technologies as it represents a significant step towards a sound theoretical foundation of explainable AI.

Counterfactual explanations are increasingly used as an Explainable Artificial Intelligence (XAI) technique to provide stakeholders of complex machine learning algorithms with explanations for data-driven decisions. The popularity of counterfactual explanations resulted in a boom in the algorithms generating them. However, not every algorithm creates uniform explanations for the same instance. Even though in some contexts multiple possible explanations are beneficial, there are circumstances where diversity amongst counterfactual explanations results in a potential disagreement problem among stakeholders. Ethical issues arise when for example, malicious agents use this diversity to fairwash an unfair machine learning model by hiding sensitive features. As legislators worldwide tend to start including the right to explanations for data-driven, high-stakes decisions in their policies, these ethical issues should be understood and addressed. Our literature review on the disagreement problem in XAI reveals that this problem has never been empirically assessed for counterfactual explanations. Therefore, in this work, we conduct a large-scale empirical analysis, on 40 datasets, using 12 explanation-generating methods, for two black-box models, yielding over 192.0000 explanations. Our study finds alarmingly high disagreement levels between the methods tested. A malicious user is able to both exclude and include desired features when multiple counterfactual explanations are available. This disagreement seems to be driven mainly by the dataset characteristics and the type of counterfactual algorithm. XAI centers on the transparency of algorithmic decision-making, but our analysis advocates for transparency about this self-proclaimed transparency

Towards a Praxis for Intercultural Ethics in Explainable AI

Chinasa T. Okolo

Explainable AI (XAI) is often promoted with the idea of helping users understand how machine learning models function and produce predictions. Still, most of these benefits are reserved for those with specialized domain knowledge, such as machine learning developers. Recent research has argued that making AI explainable can be a viable way of making AI more useful in real-world contexts, especially within low-resource domains in the Global South. While AI has transcended borders, a limited amount of work focuses on democratizing the concept of explainable AI to the "majority world", leaving much room to explore and develop new approaches within this space that cater to the distinct needs of users within culturally and socially-diverse regions. This article introduces the concept of an intercultural ethics approach to AI explainability. It examines how cultural nuances impact the adoption and use of technology, the factors that impede how technical concepts such as AI are explained, and how integrating an intercultural ethics approach in the development of XAI can improve user understanding and facilitate efficient usage of these methods.

Trust is long recognized to be an important factor in Recommender Systems (RS). However, there are different perspectives on trust and different ways to evaluate it. Moreover, a link between trust and transparency is often assumed but not always further investigated. In this paper we first go through different understandings and measurements of trust in the AI and RS community, such as demonstrated and perceived trust. We then review the relationsships between trust and transparency, as well as mental models, and investigate different strategies to achieve transparency in RS such as explanation, exploration and exploranation (i.e., a combination of exploration and explanation). We identify a need for further studies to explore these concepts as well as the relationships between them.

A stable supply of electrical energy is essential for the functioning of our society. Therefore, the electrical power grid's operation and energy and balancing markets are subject to strict regulations. As the external technical, economic, or social influences on the power grid change, these regulations must also be constantly adapted. However, whether these regulatory changes lead to the intended results is not easy to assess. Could eXplainable Artificial Intelligence (XAI) models distinguish regulatory settings and support the understanding of the effects of these changes? In this article, we explore two examples of regulatory changes in the German energy markets for bulk electricity and for reserve power. We explore the splitting of the German-Austrian bidding zone and changes in the pricing schemes of the German balancing energy market. We find that boosted tree models and feedforward neural networks before and after a regulatory change differ in their respective parametrizations. Using Shapley additive explanations, we reveal model differences, e.g. in terms of feature importances, and identify key features of these distinct models. With this study, we demonstrate how XAI can be applied to investigate system changes in power systems.

NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks

Wenkai Tan, Justus Renkhoff, Alvaro Velasquez +7

Deep Learning (DL) and Deep Neural Networks (DNNs) are widely used in various domains. However, adversarial attacks can easily mislead a neural network and lead to wrong decisions. Defense mechanisms are highly preferred in safety-critical applications. In this paper, firstly, we use the gradient class activation map (GradCAM) to analyze the behavior deviation of the VGG-16 network when its inputs are mixed with adversarial perturbation or Gaussian noise. In particular, our method can locate vulnerable layers that are sensitive to adversarial perturbation and Gaussian noise. We also show that the behavior deviation of vulnerable layers can be used to detect adversarial examples. Secondly, we propose a novel NoiseCAM algorithm that integrates information from globally and pixel-level weighted class activation maps. Our algorithm is susceptible to adversarial perturbations and will not respond to Gaussian random noise mixed in the inputs. Third, we compare detecting adversarial examples using both behavior deviation and NoiseCAM, and we show that NoiseCAM outperforms behavior deviation modeling in its overall performance. Our work could provide a useful tool to defend against certain adversarial attacks on deep neural networks.

Out-of-distribution detection is one of the most critical issue in the deployment of machine learning. The data analyst must assure that data in operation should be compliant with the training phase as well as understand if the environment has changed in a way that autonomous decisions would not be safe anymore. The method of the paper is based on eXplainable Artificial Intelligence (XAI); it takes into account different metrics to identify any resemblance between in-distribution and out of, as seen by the XAI model. The approach is non-parametric and distributional assumption free. The validation over complex scenarios (predictive maintenance, vehicle platooning, covert channels in cybersecurity) corroborates both precision in detection and evaluation of training-operation conditions proximity. Results are available via open source and open data at the following link: https://github.com/giacomo97cnr/Rule-based-ODD.

Modeling Reliance on XAI Indicating Its Purpose and Attention

Akihiro Maehigashi, Yosuke Fukuchi, Seiji Yamada

This study used XAI, which shows its purposes and attention as explanations of its process, and investigated how these explanations affect human trust in and use of AI. In this study, we generated heat maps indicating AI attention, conducted Experiment 1 to confirm the validity of the interpretability of the heat maps, and conducted Experiment 2 to investigate the effects of the purpose and heat maps in terms of reliance (depending on AI) and compliance (accepting answers of AI). The results of structural equation modeling (SEM) analyses showed that (1) displaying the purpose of AI positively and negatively influenced trust depending on the types of AI usage, reliance or compliance, and task difficulty, (2) just displaying the heat maps negatively influenced trust in a more difficult task, and (3) the heat maps positively influenced trust according to their interpretability in a more difficult task.

The increasing complexity of AI systems has led to the growth of the field of Explainable Artificial Intelligence (XAI), which aims to provide explanations and justifications for the outputs of AI algorithms. While there is considerable demand for XAI, there remains a scarcity of studies aimed at comprehensively understanding the practical distinctions among different methods and effectively aligning each method with users individual needs, and ideally, offer a mapping function which can map each user with its specific needs to a method of explainability. This study endeavors to bridge this gap by conducting a thorough review of extant research in XAI, with a specific focus on Explainable Machine Learning (XML), and a keen eye on user needs. Our main objective is to offer a classification of XAI methods within the realm of XML, categorizing current works into three distinct domains: philosophy, theory, and practice, and providing a critical review for each category. Moreover, our study seeks to facilitate the connection between XAI users and the most suitable methods for them and tailor explanations to meet their specific needs by proposing a mapping function that take to account users and their desired properties and suggest an XAI method to them. This entails an examination of prevalent XAI approaches and an evaluation of their properties. The primary outcome of this study is the formulation of a clear and concise strategy for selecting the optimal XAI method to achieve a given goal, all while delivering personalized explanations tailored to individual users.

Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance

Dangxing Chen, Luyao Zhang

Algorithm fairness in the application of artificial intelligence (AI) is essential for a better society. As the foundational axiom of social mechanisms, fairness consists of multiple facets. Although the machine learning (ML) community has focused on intersectionality as a matter of statistical parity, especially in discrimination issues, an emerging body of literature addresses another facet -- monotonicity. Based on domain expertise, monotonicity plays a vital role in numerous fairness-related areas, where violations could misguide human decisions and lead to disastrous consequences. In this paper, we first systematically evaluate the significance of applying monotonic neural additive models (MNAMs), which use a fairness-aware ML algorithm to enforce both individual and pairwise monotonicity principles, for the fairness of AI ethics and society. We have found, through a hybrid method of theoretical reasoning, simulation, and extensive empirical analysis, that considering monotonicity axioms is essential in all areas of fairness, including criminology, education, health care, and finance. Our research contributes to the interdisciplinary research at the interface of AI ethics, explainable AI (XAI), and human-computer interactions (HCIs). By evidencing the catastrophic consequences if monotonicity is not met, we address the significance of monotonicity requirements in AI applications. Furthermore, we demonstrate that MNAMs are an effective fairness-aware ML approach by imposing monotonicity restrictions integrating human intelligence.

Human activity recognition (HAR) using IMU sensors, namely accelerometer and gyroscope, has several applications in smart homes, healthcare and human-machine interface systems. In practice, the IMU-based HAR system is expected to encounter variations in measurement due to sensor degradation, alien environment or sensor noise and will be subjected to unknown activities. In view of practical deployment of the solution, analysis of statistical confidence over the activity class score are important metrics. In this paper, we therefore propose XAI-BayesHAR, an integrated Bayesian framework, that improves the overall activity classification accuracy of IMU-based HAR solutions by recursively tracking the feature embedding vector and its associated uncertainty via Kalman filter. Additionally, XAI-BayesHAR acts as an out of data distribution (OOD) detector using the predictive uncertainty which help to evaluate and detect alien input data distribution. Furthermore, Shapley value-based performance of the proposed framework is also evaluated to understand the importance of the feature embedding vector and accordingly used for model compression

On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations

Julia El Zini, Mohamad Mansour, Basel Mousi +1

Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption. In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles. First, we evaluate the strength of the extracted "rationales" in faithfully explaining the predicted outcome. Second, we measure the agreement between ExAI methods and human judgment on a homegrown dataset1 to reflect on the rationales plausibility. Our conducted experiments comprise four dimensions: (1) the underlying architectures of SA models, (2) the approach followed by the ExAI method, (3) the reasoning difficulty, and (4) the homogeneity of the ground-truth rationales. We empirically demonstrate that anchors explanations are more aligned with the human judgment and can be more confident in extracting supporting rationales. As can be foreseen, the reasoning complexity of sentiment is shown to thwart ExAI methods from extracting supporting evidence. Moreover, a remarkable discrepancy is discerned between the results of different explainability methods on the various architectures suggesting the need for consolidation to observe enhanced performance. Predominantly, transformers are shown to exhibit better explainability than convolutional and recurrent architectures. Our work paves the way towards designing more interpretable NLP models and enabling a common evaluation ground for their relative strengths and robustness.