6 papers
FORGE: Foundational Optimization Representations from Graph Embeddings
Zohair Shafi, Serdar Kadioglu
Combinatorial optimization problems are ubiquitous in science and engineering. Still, learning-based approaches to accelerate combinatorial optimization often require solving a lar…
DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
Saumya Gupta, Scott Biggs, Moritz Laber +3
Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenges posed by the high-dimensional…
Graph-SCP: Accelerating Set Cover Problems with Graph Neural Networks
Zohair Shafi, Benjamin A. Miller, Tina Eliassi-Rad +1
Machine learning (ML) approaches are increasingly being used to accelerate combinatorial optimization (CO) problems. We investigate the Set Cover Problem (SCP) and propose Graph-SC…
Defense Against Shortest Path Attacks
Benjamin A. Miller, Zohair Shafi, Wheeler Ruml +3
Identifying shortest paths between nodes in a network is an important task in many applications. Recent work has shown that a malicious actor can manipulate a graph to make traffic…
REGE: A Method for Incorporating Uncertainty in Graph Embeddings
Zohair Shafi, Germans Savcisens, Tina Eliassi-Rad
Machine learning models for graphs in real-world applications are prone to two primary types of uncertainty: (1) those that arise from incomplete and noisy data and (2) those that…
Generating Human Understandable Explanations for Node Embeddings
Zohair Shafi, Ayan Chatterjee, Tina Eliassi-Rad
Node embedding algorithms produce low-dimensional latent representations of nodes in a graph. These embeddings are often used for downstream tasks, such as node classification and…