Research Papers

Explainable Artificial Intelligence (XAI) research gained prominence in recent years in response to the demand for greater transparency and trust in AI from the user communities. This is especially critical because AI is adopted in sensitive fields such as finance, medicine etc., where implications for society, ethics, and safety are immense. Following thorough systematic evaluations, work in XAI has primarily focused on Machine Learning (ML) for categorization, decision, or action. To the best of our knowledge, no work is reported that offers an Explainable Reinforcement Learning (XRL) method for trading financial stocks. In this paper, we proposed to employ SHapley Additive exPlanation (SHAP) on a popular deep reinforcement learning architecture viz., deep Q network (DQN) to explain an action of an agent at a given instance in financial stock trading. To demonstrate the effectiveness of our method, we tested it on two popular datasets namely, SENSEX and DJIA, and reported the results.

ILMART: Interpretable Ranking with Constrained LambdaMART

Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando +2

Interpretable Learning to Rank (LtR) is an emerging field within the research area of explainable AI, aiming at developing intelligible and accurate predictive models. While most of the previous research efforts focus on creating post-hoc explanations, in this paper we investigate how to train effective and intrinsically-interpretable ranking models. Developing these models is particularly challenging and it also requires finding a trade-off between ranking quality and model complexity. State-of-the-art rankers, made of either large ensembles of trees or several neural layers, exploit in fact an unlimited number of feature interactions making them black boxes. Previous approaches on intrinsically-interpretable ranking models address this issue by avoiding interactions between features thus paying a significant performance drop with respect to full-complexity models. Conversely, ILMART, our novel and interpretable LtR solution based on LambdaMART, is able to train effective and intelligible models by exploiting a limited and controlled number of pairwise feature interactions. Exhaustive and reproducible experiments conducted on three publicly-available LtR datasets show that ILMART outperforms the current state-of-the-art solution for interpretable ranking of a large margin with a gain of nDCG of up to 8%.

Artificial Intelligence (AI) is transforming our daily life with several applications in healthcare, space exploration, banking and finance. These rapid progresses in AI have brought increasing attention to the potential impacts of AI technologies on society, with ethically questionable consequences. In recent years, several ethical principles have been released by governments, national and international organisations. These principles outline high-level precepts to guide the ethical development, deployment, and governance of AI. However, the abstract nature, diversity, and context-dependency of these principles make them difficult to implement and operationalize, resulting in gaps between principles and their execution. Most recent work analysed and summarized existing AI principles and guidelines but they did not provide findings on principle-implementation gaps and how to mitigate them. These findings are particularly important to ensure that AI implementations are aligned with ethical principles and values. In this paper, we provide a contextual and global evaluation of current ethical AI principles for all continents, with the aim to identify potential principle characteristics tailored to specific countries or applicable across countries. Next, we analyze the current level of AI readiness and current implementations of ethical AI principles in different countries, to identify gaps in the implementation of AI principles and their causes. Finally, we propose recommendations to mitigate the principle-implementation gaps.

Racial Disparities in the Enforcement of Marijuana Violations in the US

Bradley Butcher, Chris Robinson, Miri Zilka +3

Racial disparities in US drug arrest rates have been observed for decades, but their causes and policy implications are still contested. Some have argued that the disparities largely reflect differences in drug use between racial groups, while others have hypothesized that discriminatory enforcement policies and police practices play a significant role. In this work, we analyze racial disparities in the enforcement of marijuana violations in the US. Using data from the National Incident-Based Reporting System (NIBRS) and the National Survey on Drug Use and Health (NSDUH) programs, we investigate whether marijuana usage and purchasing behaviors can explain the racial composition of offenders in police records. We examine potential driving mechanisms behind these disparities and the extent to which county-level socioeconomic factors are associated with corresponding disparities. Our results indicate that the significant racial disparities in reported incidents and arrests cannot be explained by differences in marijuana days-of-use alone. Variations in the location where marijuana is purchased and in the frequency of these purchases partially explain the observed disparities. We observe an increase in racial disparities across most counties over the last decade, with the greatest increases in states that legalized the use of marijuana within this timeframe. Income, high school graduation rate, and rate of employment positively correlate with larger racial disparities, while the rate of incarceration is negatively correlated. We conclude with a discussion of the implications of the observed racial disparities in the context of algorithmic fairness.

Not only automation of manufacturing processes but also automation of automation procedures itself become increasingly relevant to automation research. In this context, automated capability assessment, mainly leveraged by deep learning systems driven from 3D CAD data, have been presented. Current assessment systems may be able to assess CAD data with regards to abstract features, e.g. the ability to automatically separate components from bulk goods, or the presence of gripping surfaces. Nevertheless, they suffer from the factor of black box systems, where an assessment can be learned and generated easily, but without any geometrical indicator about the reasons of the system's decision. By utilizing explainable AI (xAI) methods, we attempt to open up the black box. Explainable AI methods have been used in order to assess whether a neural network has successfully learned a given task or to analyze which features of an input might lead to an adversarial attack. These methods aim to derive additional insights into a neural network, by analyzing patterns from a given input and its impact to the network output. Within the NeuroCAD Project, xAI methods are used to identify geometrical features which are associated with a certain abstract feature. Within this work, a sensitivity analysis (SA), the layer-wise relevance propagation (LRP), the Gradient-weighted Class Activation Mapping (Grad-CAM) method as well as the Local Interpretable Model-Agnostic Explanations (LIME) have been implemented in the NeuroCAD environment, allowing not only to assess CAD models but also to identify features which have been relevant for the network decision. In the medium run, this might enable to identify regions of interest supporting product designers to optimize their models with regards to assembly processes.

Radiology, being one of the younger disciplines of medicine with a history of just over a century, has witnessed tremendous technological advancements and has revolutionized the way we practice medicine today. In the last few decades, medical imaging modalities have generated seismic amounts of medical data. The development and adoption of Artificial Intelligence (AI) applications using this data will lead to the next phase of evolution in radiology. It will include automating laborious manual tasks such as annotations, report-generation, etc., along with the initial radiological assessment of cases to aid radiologists in their evaluation workflow. We propose a level-wise classification for the progression of automation in radiology, explaining AI assistance at each level with corresponding challenges and solutions. We hope that such discussions can help us address the challenges in a structured way and take the necessary steps to ensure the smooth adoption of new technologies in radiology.

Artificial intelligence (AI) has brought benefits, but it may also cause harm if it is not appropriately developed. Current development is mainly driven by a "technology-centered" approach, causing many failures. For example, the AI Incident Database has documented over a thousand AI-related accidents. To address these challenges, a human-centered AI (HCAI) approach has been promoted and has received a growing level of acceptance over the last few years. HCAI calls for combining AI with user experience (UX) design will enable the development of AI systems (e.g., autonomous vehicles, intelligent user interfaces, or intelligent decision-making systems) to achieve its design goals such as usable/explainable AI, human-controlled AI, and ethical AI. While HCAI promotion continues, it has not specifically addressed the collaboration between AI and human-computer interaction (HCI) communities, resulting in uncertainty about what action should be taken by both sides to apply HCAI in developing AI systems. This Viewpoint focuses on the collaboration between the AI and HCI communities, which leads to nine recommendations for effective collaboration to enable HCAI in developing AI systems.

Comparing Human and Machine Bias in Face Recognition

Samuel Dooley, Ryan Downing, George Wei +10

Much recent research has uncovered and discussed serious concerns of bias in facial analysis technologies, finding performance disparities between groups of people based on perceived gender, skin type, lighting condition, etc. These audits are immensely important and successful at measuring algorithmic bias but have two major challenges: the audits (1) use facial recognition datasets which lack quality metadata, like LFW and CelebA, and (2) do not compare their observed algorithmic bias to the biases of their human alternatives. In this paper, we release improvements to the LFW and CelebA datasets which will enable future researchers to obtain measurements of algorithmic bias that are not tainted by major flaws in the dataset (e.g. identical images appearing in both the gallery and test set). We also use these new data to develop a series of challenging facial identification and verification questions that we administered to various algorithms and a large, balanced sample of human reviewers. We find that both computer models and human survey participants perform significantly better at the verification task, generally obtain lower accuracy rates on dark-skinned or female subjects for both tasks, and obtain higher accuracy rates when their demographics match that of the question. Computer models are observed to achieve a higher level of accuracy than the survey participants on both tasks and exhibit bias to similar degrees as the human survey participants.

Traffic accident anticipation is a vital function of Automated Driving Systems (ADSs) for providing a safety-guaranteed driving experience. An accident anticipation model aims to predict accidents promptly and accurately before they occur. Existing Artificial Intelligence (AI) models of accident anticipation lack a human-interpretable explanation of their decision-making. Although these models perform well, they remain a black-box to the ADS users, thus difficult to get their trust. To this end, this paper presents a Gated Recurrent Unit (GRU) network that learns spatio-temporal relational features for the early anticipation of traffic accidents from dashcam video data. A post-hoc attention mechanism named Grad-CAM is integrated into the network to generate saliency maps as the visual explanation of the accident anticipation decision. An eye tracker captures human eye fixation points for generating human attention maps. The explainability of network-generated saliency maps is evaluated in comparison to human attention maps. Qualitative and quantitative results on a public crash dataset confirm that the proposed explainable network can anticipate an accident on average 4.57 seconds before it occurs, with 94.02% average precision. In further, various post-hoc attention-based XAI methods are evaluated and compared. It confirms that the Grad-CAM chosen by this study can generate high-quality, human-interpretable saliency maps (with 1.23 Normalized Scanpath Saliency) for explaining the crash anticipation decision. Importantly, results confirm that the proposed AI model, with a human-inspired design, can outperform humans in the accident anticipation.

Strategies based on Explainable Artificial Intelligence - XAI have emerged in computing to promote a better understanding of predictions made by black box models. Most XAI measures used today explain these types of models, generating attribute rankings aimed at explaining the model, that is, the analysis of Attribute Importance of Model. There is no consensus on which XAI measure generates an overall explainability rank. For this reason, several proposals for tools have emerged (Ciu, Dalex, Eli5, Lofo, Shap and Skater). An experimental benchmark of explainable AI techniques capable of producing global explainability ranks based on tabular data related to different problems and ensemble models are presented herein. Seeking to answer questions such as "Are the explanations generated by the different measures the same, similar or different?" and "How does data complexity play along model explainability?" The results from the construction of 82 computational models and 592 ranks shed some light on the other side of the problem of explainability: dataset complexity!

In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern. However, the link between the fairness of the black-box model and the behavior of explanations for the black-box is unclear. We focus on explanations applied to tabular datasets, suggesting that explanations do not necessarily preserve the fairness properties of the black-box algorithm. In other words, explanation algorithms can ignore or obscure critical relevant properties, creating incorrect or misleading explanations. More broadly, we propose future research directions for evaluating and generating explanations such that they are informative and relevant from a fairness perspective.

Deep learning has now become the de facto approach to the recognition of anomalies in medical imaging. Their 'black box' way of classifying medical images into anomaly labels poses problems for their acceptance, particularly with clinicians. Current explainable AI methods offer justifications through visualizations such as heat maps but cannot guarantee that the network is focusing on the relevant image region fully containing the anomaly. In this paper, we develop an approach to explainable AI in which the anomaly is assured to be overlapping the expected location when present. This is made possible by automatically extracting location-specific labels from textual reports and learning the association of expected locations to labels using a hybrid combination of Bi-Directional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM) and DenseNet-121. Use of this expected location to bias the subsequent attention-guided inference network based on ResNet101 results in the isolation of the anomaly at the expected location when present. The method is evaluated on a large chest X-ray dataset.