Graph-SCP: Accelerating Set Cover Problems with Graph Neural Networks

no code implementations • 12 Oct 2023 • Zohair Shafi, Benjamin A. Miller, Tina Eliassi-Rad, Rajmonda S. Caceres

We look specifically at the Set Cover Problem (SCP) and propose Graph-SCP, a graph neural network method that can augment existing optimization solvers by learning to identify a much smaller sub-problem that contains the solution space.

Combinatorial Optimization

GRASP: Accelerating Shortest Path Attacks via Graph Attention

no code implementations • 12 Oct 2023 • Zohair Shafi, Benjamin A. Miller, Ayan Chatterjee, Tina Eliassi-Rad, Rajmonda S. Caceres

We consider an APX-hard problem, where an adversary aims to attack shortest paths in a graph by removing the minimum number of edges.

Combinatorial Optimization Graph Attention

AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands

2 code implementations • 25 Dec 2021 • Ayan Chatterjee, Robin Walters, Zohair Shafi, Omair Shafi Ahmed, Michael Sebek, Deisy Gysi, Rose Yu, Tina Eliassi-Rad, Albert-László Barabási, Giulia Menichetti

Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery.

Drug Discovery Unsupervised Pre-training

RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity

no code implementations • 16 Mar 2021 • David Liu, Zohair Shafi, William Fleisher, Tina Eliassi-Rad, Scott Alfeld

We present RAWLSNET, a system for altering Bayesian Network (BN) models to satisfy the Rawlsian principle of fair equality of opportunity (FEO).