VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Under review at TVCG, 2021

Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper, we utilize interactive visualization to increase the interpretability and accessibility of a collection of state-of-the-art debiasing techniques…

A. Rathore, S. Dev, J.M. Philips , S. Srikumar, et al. View manuscript

Mapper Interactive: A Scalable, Extendable, and Interactive Toolbox for the Visual Exploration of High-Dimensional Data.

IEEE 14th Pacific Visualization Symposium (PacificVis), 2021

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…

Y. Zhou, N. Chalapathi, A. Rathore, Y. Zhao and B. Wang. View manuscript

TopoAct: Exploring the Shape of Activations in Deep Learning

Computer Graphics Forum, 2021

Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e., combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations…

A. Rathore, N. Chalapathi, S. Palande, B. Wang. View manuscript

Autism Classification Using Topological Features and Deep Learning: A Cautionary Tale

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019

The identification of autistic individuals using resting state functional connectivity networks can provide an objective diagnostic method for autism spectrum disorder (ASD). The present state-of-the-art machine learning model using deep learning has a classification accuracy of 70.2% on the ABIDE (Autism Brain Imaging Data Exchange) data set. In this paper, we explore the utility of topological features in the classification of ASD versus typically developing control subjects…

A. Rathore, S. Palande, J. S. Anderson, et al. View manuscript