activity
20172022
most citedGenerative Counterfactual Introspection for Explainable Deep Learning

32 citations · 46 across the 10 of their papers we have counts for

collaborators

9 papers

cs.LG20212 cited

Reliable Graph Neural Network Explanations Through Adversarial Training

Donald Loveland, Shusen Liu, Bhavya Kailkhura +2

Graph neural network (GNN) explanations have largely been facilitated through post-hoc introspection. While this has been deemed successful, many post-hoc explanation methods have…

cs.LG20205 cited

Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design

Shusen Liu, Bhavya Kailkhura, Jize Zhang +4

The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in buildin…

cs.CV20202 cited

Actionable Attribution Maps for Scientific Machine Learning

Shusen Liu, Bhavya Kailkhura, Jize Zhang +4

The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in buildin…

cs.DC2019

Parallelizing Training of Deep Generative Models on Massive Scientific Datasets

Sam Ade Jacobs, Brian Van Essen, David Hysom +11

Training deep neural networks on large scientific data is a challenging task that requires enormous compute power, especially if no pre-trained models exist to initialize the proce…

physics.comp-ph20192 cited

Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion

Rushil Anirudh, Jayaraman J. Thiagarajan, Shusen Liu +2

There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-drive…

cs.LG20191 cited

Function Preserving Projection for Scalable Exploration of High-Dimensional Data

Shusen Liu, Rushil Anirudh, Jayaraman J. Thiagarajan +1

We present function preserving projections (FPP), a scalable linear projection technique for discovering interpretable relationships in high-dimensional data. Conventional dimensio…