47 citations · 122 across the 11 of their papers we have counts for
12 papers
Unveiling the Impact of Local Homophily on GNN Fairness: In-Depth Analysis and New Benchmarks
Donald Loveland, Danai Koutra
Graph Neural Networks (GNNs) often struggle to generalize when graphs exhibit both homophily (same-class connections) and heterophily (different-class connections). Specifically, G…
Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank
Donald Loveland, Xinyi Wu, Tong Zhao +3
Collaborative Filtering (CF) methods dominate real-world recommender systems given their ability to learn high-quality, sparse ID-embedding tables that effectively capture user pre…
On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks
Donald Loveland, Jiong Zhu, Mark Heimann +3
Graph Neural Network (GNN) research has highlighted a relationship between high homophily (i.e., the tendency of nodes of the same class to connect) and strong predictive performan…
On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods
Donald Loveland, Jiong Zhu, Mark Heimann +3
We study the task of node classification for graph neural networks (GNNs) and establish a connection between group fairness, as measured by statistical parity and equal opportunity…
Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning
Ioannis Tsaknakis, Bhavya Kailkhura, Sijia Liu +4
Using deep learning (DL) to accelerate and/or improve scientific workflows can yield discoveries that are otherwise impossible. Unfortunately, DL models have yielded limited succes…
FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing
Donald Loveland, Jiayi Pan, Aaresh Farrokh Bhathena +1
Graph Neural Networks (GNNs) have proven to excel in predictive modeling tasks where the underlying data is a graph. However, as GNNs are extensively used in human-centered applica…
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…
How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
Jiong Zhu, Junchen Jin, Donald Loveland +2
We bridge two research directions on graph neural networks (GNNs), by formalizing the relation between heterophily of node labels (i.e., connected nodes tend to have dissimilar lab…
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…
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…
Generative Counterfactual Introspection for Explainable Deep Learning
Shusen Liu, Bhavya Kailkhura, Donald Loveland +1
In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretat…
Predicting Compressive Strength of Consolidated Molecular Solids Using Computer Vision and Deep Learning
Brian Gallagher, Matthew Rever, Donald Loveland +6
We explore the application of computer vision and machine learning (ML) techniques to predict material properties (e.g. compressive strength) based on SEM images. We show that it's…