Related papers: Balancing expressiveness and inexpressiveness in v…

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

Many data problems are solved when the right view of a combination of datasets is identified. Finding such a view is challenging because of the many tables spread across many databases, data lakes, and cloud storage in modern organizations.…

We study explanation design in algorithmic decision making with strategic agents, individuals who may modify their inputs in response to explanations of a decision maker's (DM's) predictive model. As the demand for transparent algorithmic…

Although visualization tools are widely available and accessible, not everyone knows the best practices and guidelines for creating accurate and honest visual representations of data. Numerous books and articles have been written to expose…

We present an empirical study aimed at analysing the use of viewpoints in an industrial Concurrent Engineering context. Our focus is on the viewpoints expressed in the argumentative process taking place in evaluation meetings. Our results…

We present associative and causal views of differential privacy. Under the associative view, the possibility of dependencies between data points precludes a simple statement of differential privacy's guarantee as conditioning upon a single…

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of…

Providing opinions through labeling of images, tweets, etc. have drawn immense interest in crowdsourcing markets. This invokes a major challenge of aggregating multiple opinions received from different crowd workers for deriving the final…

Despite the importance of viewers' trust in data visualization, there is a lack of research on the viewers' own perspective on their trust. In addition, much of the research on trust remains relatively theoretical and inaccessible for…

Recent studies investigated the challenge of assessing the strength of a given claim extracted from a dataset, particularly the claim's potential of being misleading and cherry-picked. We focus on claims that compare answers to an aggregate…

Views on RDF datasets have been discussed in several works, nevertheless there is no consensus on their definition nor the requirements they should fulfill. In traditional data management systems, views have proved to be useful in different…

Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The…

Open data are held to contribute to a wide variety of social and political goals, including strengthening transparency, public participation and democratic accountability, promoting economic growth and innovation, and enabling greater…

A growing number of efforts aim to understand what people see when using a visualization. These efforts provide scientific grounding to complement design intuitions, leading to more effective visualization practice. However, published…

Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…

Fairness concerns about algorithmic decision-making systems have been mainly focused on the outputs (e.g., the accuracy of a classifier across individuals or groups). However, one may additionally be concerned with fairness in the inputs.…

Visual representations are defined in terms of minimal sufficient statistics of visual data, for a class of tasks, that are also invariant to nuisance variability. Minimal sufficiency guarantees that we can store a representation in lieu of…

The input data features set for many data driven tasks is high-dimensional while the intrinsic dimension of the data is low. Data analysis methods aim to uncover the underlying low dimensional structure imposed by the low dimensional hidden…

We believe that 3D visualisations should not be used alone; by coincidentally displaying alternative views the user can gain the best understanding of all situations. The different presentations signify manifold meanings and afford…

The analysis of structured complex data, such as clustered graph based datasets, usually applies a variety of visual representation techniques and formats. The majority of currently available tools and approaches to exploratory…