Explainable AI enables a better adoption of AI by increasing the transparency and trustworthiness of AI solutions and outcomes. Explainable AI also reduces the risks associated with regulatory and reputational accountability for safety and fairness. Increasingly, these solutions are not only showing data scientists the input and the output of a model, but are also explaining the reasons the system selected particular models and the techniques applied by augmented data science and ML. Bias has been a long-standing risk in training AI models. Bias could be based on race, gender, age or location.

As a field of AI, Machine Reasoning (MR) uses largely symbolic means to formalize and emulate abstract reasoning. Studies in early MR have notably started inquiries into Explainable AI (XAI) -- arguably one of the biggest concerns today for the AI community. Work on explainable MR as well as on MR approaches to explainability in other areas of AI has continued ever since. It is especially potent in modern MR branches, such as argumentation, constraint and logic programming, planning. We hereby aim to provide a selective overview of MR explainability techniques and studies in hopes that insights from this long track of research will complement well the current XAI landscape. This document reports our work in-progress on MR explainability.

Strategic argumentation provides a simple model of disputation and negotiation among agents. Although agents might be expected to act in our best interests, there is little that enforces such behaviour. (Maher, 2016) introduced a model of corruption and resistance to corruption within strategic argumentation. In this paper we identify corrupt behaviours that are not detected in that formulation. We strengthen the model to detect such behaviours, and show that, under the strengthened model, all the strategic aims in (Maher, 2016) are resistant to corruption.

This paper is a note on new directions and methodologies for validation and explanation of Machine Learning (ML) models employed for retail credit scoring in finance. Our proposed framework draws motivation from the field of Artificial Intelligence (AI) security and adversarial ML where the need for certifying the performance of the ML algorithms in the face of their overwhelming complexity poses a need for rethinking the traditional notions of model architecture selection, sensitivity analysis and stress testing. Our point of view is that the phenomenon of adversarial perturbations when detached from the AI security domain, has purely algorithmic roots and fall within the scope of model risk assessment. We propose a model criticism and explanation framework based on adversarially generated counterfactual examples for tabular data. A counterfactual example to a given instance in this context is defined as a synthetically generated data point sampled from the estimated data distribution which is treated differently by a model. The counterfactual examples can be used to provide a black-box instance-level explanation of the model behaviour as well as studying the regions in the input space where the model performance deteriorates. Adversarial example generating algorithms are extensively studied in the image and natural language processing (NLP) domains. However, most financial data come in tabular format and naive application of the existing techniques on this class of datasets generates unrealistic samples. In this paper, we propose a counterfactual example generation method capable of handling tabular data including discrete and categorical variables. Our proposed algorithm uses a gradient-free optimization based on genetic algorithms and therefore is applicable to any classification model.

Because in military situations, as well as for self-driving cars, information must be processed faster than humans can achieve, determination of context computationally, also known as situational assessment, is increasingly important. In this article, we introduce the topic of context, and we discuss what is known about the heretofore intractable research problem on the effects of interdependence, present in the best of human teams; we close by proposing that interdependence must be mastered mathematically to operate human-machine teams efficiently, to advance theory, and to make the machine actions directed by AI explainable to team members and society. The special topic articles in this issue and a subsequent issue of AI Magazine review ongoing mature research and operational programs that address context for human-machine teams. In 1983, William Lawless blew the whistle on Department of Energy (DOE) mismanagement of military radioactive wastes. After his PhD, he joined DOE's citizen advisory board at its Savannah River Site where he coauthored over 100 recommendations on its cleanup.

The City of London in Canada is implementing an artificial intelligence (AI) tool it has developed internally to predict and prevent homelessness. The Chronic Homelessness Artificial Intelligence (CHAI) model uses machine learning to forecast the probability of an individual in the city's shelter system becoming chronically homeless within the next six months – that is, remaining in the shelter system for more than 180 days in a year. In July, 312 people in London were chronically homeless. The tool was developed in-house with support from a consultant, and could help other cities – particularly those in Canada – deploy similar systems quickly. The CHAI model grew out of London's adoption of the federal Homeless Individuals and Families Information System (HIFIS), which is designed to provide a clearer picture of homelessness in communities and support organisations to work collaboratively.

Applying machine learning (ML) on multivariate time series data has growing popularity in many application domains, including in computer system management. For example, recent high performance computing (HPC) research proposes a variety of ML frameworks that use system telemetry data in the form of multivariate time series so as to detect performance variations, perform intelligent scheduling or node allocation, and improve system security. Common barriers for adoption for these ML frameworks include the lack of user trust and the difficulty of debugging. These barriers need to be overcome to enable the widespread adoption of ML frameworks in production systems. To address this challenge, this paper proposes a novel explainability technique for providing counterfactual explanations for supervised ML frameworks that use multivariate time series data. The proposed method outperforms state-of-the-art explainability methods on several different ML frameworks and data sets in metrics such as faithfulness and robustness. The paper also demonstrates how the proposed method can be used to debug ML frameworks and gain a better understanding of HPC system telemetry data.

Machine learning and artificial intelligence are helping automate an ever-increasing array of tasks, with ever-increasing accuracy.

With machine learning models being increasingly applied to various decision-making scenarios, people have spent growing efforts to make machine learning models more transparent and explainable. Among various explanation techniques, counterfactual explanations have the advantages of being human-friendly and actionable -- a counterfactual explanation tells the user how to gain the desired prediction with minimal changes to the input. Besides, counterfactual explanations can also serve as efficient probes to the models' decisions. In this work, we exploit the potential of counterfactual explanations to understand and explore the behavior of machine learning models. We design DECE, an interactive visualization system that helps understand and explore a model's decisions on individual instances and data subsets, supporting users ranging from decision-subjects to model developers. DECE supports exploratory analysis of model decisions by combining the strengths of counterfactual explanations at instance- and subgroup-levels. We also introduce a set of interactions that enable users to customize the generation of counterfactual explanations to find more actionable ones that can suit their needs. Through three use cases and an expert interview, we demonstrate the effectiveness of DECE in supporting decision exploration tasks and instance explanations.

Artificial intelligence (AI) has become prevalent in our everyday technologies and impacts both individuals and communities. The explainable AI (XAI) scholarship has explored the philosophical nature of explanation and technical explanations, which are usually driven by experts in lab settings and can be challenging for laypersons to understand. In addition, existing XAI research tends to focus on the individual level. Little is known about how people understand and explain AI-led decisions in the community context. Drawing from XAI and activity theory, a foundational HCI theory, we theorize how explanation is situated in a community's shared values, norms, knowledge, and practices, and how situated explanation mediates community-AI interaction. We then present a case study of AI-led moderation, where community members collectively develop explanations of AI-led decisions, most of which are automated punishments. Lastly, we discuss the implications of this framework at the intersection of CSCW, HCI, and XAI.