4 papers · 1 filter
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
Roman Bresson, Konstantinos Divriotis, Johannes F. Lutzeyer +2
We introduce GraViti, a transformer-based graph-level variational autoencoder that maps entire graphs to compact latent vectors. This design produces a true graph-level latent spac…
Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings
Nikolaos Nakis, Chrysoula Kosma, Giannis Nikolentzos +3
Autoencoders based on Graph Neural Networks (GNNs) have garnered significant attention in recent years for their ability to extract informative latent representations, characterizi…
The Signed Two-Space Proximity Model for Learning Representations in Protein-Protein Interaction Networks
Nikolaos Nakis, Chrysoula Kosma, Anastasia Brativnyk +3
Accurately predicting complex protein-protein interactions (PPIs) is crucial for decoding biological processes, from cellular functioning to disease mechanisms. However, experiment…
Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Models
Iakovos Evdaimon, Giannis Nikolentzos, Christos Xypolopoulos +4
Graph generation has emerged as a crucial task in machine learning, with significant challenges in generating graphs that accurately reflect specific properties. Existing methods o…