AI systems are becoming omnipresent in our daily lives, but they can sometimes be a source of bias for disadvantaged groups. Lack of fairness in AI systems is not just an engineering issue that influences public policy, it also has important implications for business ethics and corporate social responsibility. To educate nontechnical students at the business school, we have developed educational modules on fairness in AI that convey the importance of making not just accurate but also equitable business decisions. We introduce an educational module with six interactive components that illustrate how to detect, quantify, and mitigate biases in a logistic regression model. When such a module was deployed in a "Fair Algorithms for Business" course, it was shown to increase students’ engagement and understanding. We further conducted a user study with 413 participants to examine whether adding visualizations and interactions (or not) could lead to an increased understanding of fairness concepts.

Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture resulting in high-dimensional, difficult to interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper we apply cutting edge techniques from TDA with the goal of gaining insight towards interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers and discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight as to how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.

We study hypergraph visualization via its topological simplification. We explore both vertex simplification and hyperedge simplification of hypergraphs using tools from topological data analysis. In particular, we transform a hypergraph into its graph representations, known as the line graph and clique expansion. A topological simplification of such a graph representation induces a simplification of the hypergraph. In simplifying a hypergraph, we allow vertices to be combined if they belong to almost the same set of hyperedges, and hyperedges to be merged if they share almost the same set of vertices. Our proposed approaches are general and mathematically justifiable, and put vertex simplification and hyperedge simplification in a unifying framework.

Abstract We propose a novel method for the computation of Jacobi sets in 2D domains. The Jacobi set is a topological descriptor based on Morse theory that captures gradient alignments among multiple scalar fields, which is useful for multi-field visualization. Previous Jacobi set computations use piecewise linear approximations on triangulations that result in discretization artifacts like zig-zag patterns. In this paper, we utilize a local bilinear method to obtain a more precise approximation of Jacobi sets by preserving the topology and improving the geometry. Consequently, zig-zag patterns on edges are avoided, resulting in a smoother Jacobi set representation. Our experiments show a better convergence with increasing resolution compared to the piecewise linear method. We utilize this advantage with an efficient local subdivision scheme. Finally, our approach is evaluated qualitatively and quantitatively in comparison with previous methods for different mesh resolutions and across a number of synthetic and real-world examples.

The mapper algorithm is a popular tool from topological data analysis for extracting topological summaries of high-dimensional datasets. In this paper, we present Mapper Interactive, a web-based framework for the interactive analysis and visualization of high-dimensional point cloud data. It implements the mapper algorithm in an interactive, scalable, and easily extendable way, thus supporting practical data analysis. In particular, its command-line API can compute mapper graphs for 1 million points of 256 dimensions in about 3 minutes (4 times faster than the vanilla implementation). Its visual interface allows on-the-fly computation and manipulation of the mapper graph based on user-specified parameters and supports the addition of new analysis modules with a few lines of code. Mapper Interactive makes the mapper algorithm accessible to nonspecialists and accelerates topological analytics workflows.

The mapper construction is a widely used tool from topological data analysis in obtaining topological summaries of large, high-dimensional point cloud data. It has enjoyed great success in data science, including cancer research, sports analytics, and visualization. However, developing practical and automatic parameter selection for the mapper construction remains a challenging open problem for both the topological analysis and visualization communities. In this paper, we focus on parameter selection for the 1-dimensional skeleton of the mapper construction, called the mapper graph. Specifically, we explore how information criteria used in the X-means clustering algorithm can inform and generate adaptive covers for mapper graphs. Our approach thus makes novel progress towards automatic parameter selection for the mapper construction using information theory.

Discrete stratified Morse theory, first introduced by Knudson and Wang, works toward a discrete analogue of Goresky and MacPherson’s stratified Morse theory. It is inspired by the works of Forman on discrete Morse theory by generalizing stratified Morse theory to finite simplicial complexes. The class of discrete stratified Morse functions is much larger than that of discrete Morse functions. Any arbitrary real-valued function defined on a finite simplicial complex can be made into a discrete stratified Morse function with the proper stratification of the underlying complex. An algorithm is given by Knudson and Wang that constructs a discrete stratified Morse function on any finite simplicial complex equipped with an arbitrary real-valued function. Our media contribution is an open-sourced visualization tool that implements such an algorithm for 2-complexes embedded in the plane, and provides an interactive demo for users to explore the algorithmic process and to perform homotopy-preserving simplification of the resulting stratified complex.