Related papers: Surfacing Visualization Mirages
Comparative simulation studies are workhorse tools for benchmarking statistical methods. As with other empirical studies, the success of simulation studies hinges on the quality of their design, execution and reporting. If not conducted…
We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on `HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found that these…
Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results. However, one of the deleterious side-effects of these advances is the emergence of…
In machine learning, concept drift is an evolution of information that invalidates the current data model. It happens when the statistical properties of the input data change over time in unforeseen ways. Concept drift detection is crucial…
Metamorphic testing has become one mainstream technique to address the notorious oracle problem in software testing, thanks to its great successes in revealing real-life bugs in a wide variety of software systems. Metamorphic relations, the…
In contrast to objectively measurable aspects (such as accuracy, reading speed, or memorability), the subjective experience of visualizations has only recently gained importance, and we have less experience how to measure it. We explore how…
Visual analytics systems such as Tableau are increasingly popular for interactive data exploration. These tools, however, do not currently assist users with detecting or resolving potential data quality problems including the well-known…
Data visualizations have been widely used on mobile devices like smartphones for various tasks (e.g., visualizing personal health and financial data), making it convenient for people to view such data anytime and anywhere. However, others…
Missing data is an important problem in machine learning practice. Starting from the premise that imputation methods should preserve the causal structure of the data, we develop a regularization scheme that encourages any baseline…
Through purposeful introduction of malicious transactions (tracking transactions) into randomly select nodes of a (database) graph, soiled and clean segments are identified. Soiled and clean measures corresponding those segments are then…
The aim of visualization is to support people in dealing with large and complex information structures, to make these structures more comprehensible, facilitate exploration, and enable knowledge discovery. However, users often have problems…
Software systems are not static, they have to undergo frequent changes to stay fit for purpose, and in the process of doing so, their complexity increases. It has been observed that this process often leads to the erosion of the systems…
The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many…
Software visualization seeks to represent software artifacts graphical-ly in two or three dimensions, with the goal of enhancing comprehension, anal-ysis, maintenance, and evolution of the source code. In this context, visualiza-tions…
In the face of complex decisions, people often engage in a three-stage process that spans from (1) exploring and analyzing pertinent information (intelligence); (2) generating and exploring alternative options (design); and ultimately…
Understanding causal relationships among the variables of a system is paramount to explain and control its behavior. For many real-world systems, however, the true causal graph is not readily available and one must resort to predictions…
Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can…
The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading…
Modern machine learning frameworks support very large models by incorporating parallelism and optimization techniques. Yet, these very techniques add new layers of complexity, introducing silent errors that severely degrade model…
Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge these claims by introducing Mirage, a representation-level…