AI RESEARCH
Graph Neural Network-Informed Predictive Flows for Faster Ford-Fulkerson and PAC-Learnability
arXiv CS.LG
•
ArXi:2604.21175v1 Announce Type: new We propose a learning-augmented framework for accelerating max-flow computation and image segmentation by integrating Graph Neural Networks (GNNs) with the Ford-Fulkerson algorithm. Rather than predicting initial flows, our method learns edge importance probabilities to guide augmenting path selection.