2 papers
cs.LG2025
DeltaGNN: Graph Neural Network with Information Flow Control
Kevin Mancini, Islem Rekik
Graph Neural Networks (GNNs) are popular deep learning models designed to process graph-structured data through recursive neighborhood aggregations in the message passing process.…
cs.LG2024
DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling
K. Mancini, I. Rekik
Graph Neural Networks (GNNs) have proven effective in various medical imaging applications, such as automated disease diagnosis. However, due to the local neighborhood aggregation…