Research Papers

EXplainable Artificial Intelligence (XAI) aims to help users to grasp the reasoning behind the predictions of an Artificial Intelligence (AI) system. Many XAI approaches have emerged in recent years. Consequently, a subfield related to the evaluation of XAI methods has gained considerable attention, with the aim to determine which methods provide the best explanation using various approaches and criteria. However, the literature lacks a comparison of the evaluation metrics themselves, that one can use to evaluate XAI methods. This work aims to fill this gap by comparing 14 different metrics when applied to nine state-of-the-art XAI methods and three dummy methods (e.g., random saliency maps) used as references. Experimental results show which of these metrics produces highly correlated results, indicating potential redundancy. We also demonstrate the significant impact of varying the baseline hyperparameter on the evaluation metric values. Finally, we use dummy methods to assess the reliability of metrics in terms of ranking, pointing out their limitations.

Distributed trust is a nebulous concept that has evolved from different perspectives in recent years. While one can attribute its current prominence to blockchain and cryptocurrency, the distributed trust concept has been cultivating progress in federated learning, trustworthy and responsible AI in an ecosystem setting, data sharing, privacy issues across organizational boundaries, and zero trust cybersecurity. This paper will survey the concept of distributed trust in multiple disciplines. It will take a system/software architecture point of view to look at trust redistribution/shift and the associated tradeoffs in systems and applications enabled by distributed trust technologies.

The deployment and use of AI systems should be both safe and broadly ethically acceptable. The principles-based ethics assurance argument pattern is one proposal in the AI ethics landscape that seeks to support and achieve that aim. The purpose of this argument pattern or framework is to structure reasoning about, and to communicate and foster confidence in, the ethical acceptability of uses of specific real-world AI systems in complex socio-technical contexts. This paper presents the interim findings of a case study applying this ethics assurance framework to the use of Dora, an AI-based telemedicine system, to assess its viability and usefulness as an approach. The case study process to date has revealed some of the positive ethical impacts of the Dora platform, as well as unexpected insights and areas to prioritise for evaluation, such as risks to the frontline clinician, particularly in respect of clinician autonomy. The ethics assurance argument pattern offers a practical framework not just for identifying issues to be addressed, but also to start to construct solutions in the form of adjustments to the distribution of benefits, risks and constraints on human autonomy that could reduce ethical disparities across affected stakeholders. Though many challenges remain, this research represents a step in the direction towards the development and use of safe and ethically acceptable AI systems and, ideally, a shift towards more comprehensive and inclusive evaluations of AI systems in general.

Explainable artificial intelligence (AI) techniques are increasingly being explored to provide insights into why AI and machine learning (ML) models provide a certain outcome in various applications. However, there has been limited exploration of explainable AI techniques on time-series data, especially in the healthcare context. In this paper, we describe a threshold-based method that utilizes a weakly supervised model and a gradient-based explainable AI technique (i.e. saliency map) and explore its feasibility to identify salient frames of time-series data. Using the dataset from 15 post-stroke survivors performing three upper-limb exercises and labels on whether a compensatory motion is observed or not, we implemented a feed-forward neural network model and utilized gradients of each input on model outcomes to identify salient frames that involve compensatory motions. According to the evaluation using frame-level annotations, our approach achieved a recall of 0.96 and an F2-score of 0.91. Our results demonstrated the potential of a gradient-based explainable AI technique (e.g. saliency map) for time-series data, such as highlighting the frames of a video that therapists should focus on reviewing and reducing the efforts on frame-level labeling for model training.

Climate change is the defining issue of our time, and we are at a defining moment. Various interest groups, social movement organizations, and individuals engage in collective action on this issue on social media. In addition, issue advocacy campaigns on social media often arise in response to ongoing societal concerns, especially those faced by energy industries. Our goal in this paper is to analyze how those industries, their advocacy group, and climate advocacy group use social media to influence the narrative on climate change. In this work, we propose a minimally supervised model soup [57] approach combined with messaging themes to identify the stances of climate ads on Facebook. Finally, we release our stance dataset, model, and set of themes related to climate campaigns for future work on opinion mining and the automatic detection of climate change stances.

Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models

Daniel G. Krakowczyk, Paul Prasse, David R. Reich +3

Recent work in XAI for eye tracking data has evaluated the suitability of feature attribution methods to explain the output of deep neural sequence models for the task of oculomotric biometric identification. These methods provide saliency maps to highlight important input features of a specific eye gaze sequence. However, to date, its localization analysis has been lacking a quantitative approach across entire datasets. In this work, we employ established gaze event detection algorithms for fixations and saccades and quantitatively evaluate the impact of these events by determining their concept influence. Input features that belong to saccades are shown to be substantially more important than features that belong to fixations. By dissecting saccade events into sub-events, we are able to show that gaze samples that are close to the saccadic peak velocity are most influential. We further investigate the effect of event properties like saccadic amplitude or fixational dispersion on the resulting concept influence.

There has been a surge in Explainable-AI (XAI) methods that provide insights into the workings of Deep Neural Network (DNN) models. Integrated Gradients (IG) is a popular XAI algorithm that attributes relevance scores to input features commensurate with their contribution to the model's output. However, it requires multiple forward \& backward passes through the model. Thus, compared to a single forward-pass inference, there is a significant computational overhead to generate the explanation which hinders real-time XAI. This work addresses the aforementioned issue by accelerating IG with a hardware-aware algorithm optimization. We propose a novel non-uniform interpolation scheme to compute the IG attribution scores which replaces the baseline uniform interpolation. Our algorithm significantly reduces the total interpolation steps required without adversely impacting convergence. Experiments on the ImageNet dataset using a pre-trained InceptionV3 model demonstrate \textit{2.6-3.6}$\times$ performance speedup on GPU systems for iso-convergence. This includes the minimal \textit{0.2-3.2}\% latency overhead introduced by the pre-processing stage of computing the non-uniform interpolation step-sizes.

Several policy options exist, or have been proposed, to further responsible artificial intelligence (AI) development and deployment. Institutions, including U.S. government agencies, states, professional societies, and private and public sector businesses, are well positioned to implement these policies. However, given limited resources, not all policies can or should be equally prioritized. We define and review nine suggested policies for furthering responsible AI, rank each policy on potential use and impact, and recommend prioritization relative to each institution type. We find that pre-deployment audits and assessments and post-deployment accountability are likely to have the highest impact but also the highest barriers to adoption. We recommend that U.S. government agencies and companies highly prioritize development of pre-deployment audits and assessments, while the U.S. national legislature should highly prioritize post-deployment accountability. We suggest that U.S. government agencies and professional societies should highly prioritize policies that support responsible AI research and that states should highly prioritize support of responsible AI education. We propose that companies can highly prioritize involving community stakeholders in development efforts and supporting diversity in AI development. We advise lower levels of prioritization across institutions for AI ethics statements and databases of AI technologies or incidents. We recognize that no one policy will lead to responsible AI and instead advocate for strategic policy implementation across institutions.

Novel data sensing and AI technologies are finding practical use in the analysis of crisis resilience, revealing the need to consider how responsible artificial intelligence (AI) practices can mitigate harmful outcomes and protect vulnerable populations. In this paper, we present a responsible AI roadmap that is embedded in the Crisis Information Management Circle. This roadmap includes six propositions to highlight and address important challenges and considerations specifically related to responsible AI for crisis resilience management. We cover a wide spectrum of interwoven challenges and considerations pertaining to the responsible collection, analysis, sharing, and use of information such as equity, fairness, biases, explainability and transparency, accountability, privacy and security, inter-organizational coordination, and public engagement. Through examining issues around AI systems for crisis resilience management, we dissect the inherent complexities of information management and decision-making in crises and highlight the urgency of responsible AI research and practice. The ideas laid out in this paper are the first attempt in establishing a roadmap for researchers, practitioners, developers, emergency managers, humanitarian organizations, and public officials to address important considerations for responsible AI pertaining to crisis resilience management.

This paper summarizes and evaluates various approaches, methods, and techniques for pursuing fairness in artificial intelligence (AI) systems. It examines the merits and shortcomings of these measures and proposes practical guidelines for defining, measuring, and preventing bias in AI. In particular, it cautions against some of the simplistic, yet common, methods for evaluating bias in AI systems, and offers more sophisticated and effective alternatives. The paper also addresses widespread controversies and confusions in the field by providing a common language among different stakeholders of high-impact AI systems. It describes various trade-offs involving AI fairness, and provides practical recommendations for balancing them. It offers techniques for evaluating the costs and benefits of fairness targets, and defines the role of human judgment in setting these targets. This paper provides discussions and guidelines for AI practitioners, organization leaders, and policymakers, as well as various links to additional materials for a more technical audience. Numerous real-world examples are provided to clarify the concepts, challenges, and recommendations from a practical perspective.

A Human-Centric Assessment Framework for AI

Sascha Saralajew, Ammar Shaker, Zhao Xu +5

With the rise of AI systems in real-world applications comes the need for reliable and trustworthy AI. An essential aspect of this are explainable AI systems. However, there is no agreed standard on how explainable AI systems should be assessed. Inspired by the Turing test, we introduce a human-centric assessment framework where a leading domain expert accepts or rejects the solutions of an AI system and another domain expert. By comparing the acceptance rates of provided solutions, we can assess how the AI system performs compared to the domain expert, and whether the AI system's explanations (if provided) are human-understandable. This setup -- comparable to the Turing test -- can serve as a framework for a wide range of human-centric AI system assessments. We demonstrate this by presenting two instantiations: (1) an assessment that measures the classification accuracy of a system with the option to incorporate label uncertainties; (2) an assessment where the usefulness of provided explanations is determined in a human-centric manner.

The issue of fairness in machine learning stems from the fact that historical data often displays biases against specific groups of people which have been underprivileged in the recent past, or still are. In this context, one of the possible approaches is to employ fair representation learning algorithms which are able to remove biases from data, making groups statistically indistinguishable. In this paper, we instead develop a fair representation learning algorithm which is able to map individuals belonging to different groups in a single group. This is made possible by training a pair of Normalizing Flow models and constraining them to not remove information about the ground truth by training a ranking or classification model on top of them. The overall, ``chained'' model is invertible and has a tractable Jacobian, which allows to relate together the probability densities for different groups and ``translate'' individuals from one group to another. We show experimentally that our methodology is competitive with other fair representation learning algorithms. Furthermore, our algorithm achieves stronger invariance w.r.t. the sensitive attribute.