5 papers
Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
Dionisia Naddeo, Jonas Linkerhägner, Nicola Toschi +2
Many complex networks exhibit hierarchical, tree-like structures, making hyperbolic space a natural candidate wherein to learn representations of them. Based on this observation, H…
Benchmarking Graph Neural Networks in Solving Hard Constraint Satisfaction Problems
Geri Skenderi, Lorenzo Buffoni, Francesco D'Amico +6
Graph neural networks (GNNs) are increasingly applied to hard optimization problems, often claiming superiority over classical heuristics. However, such claims risk being unsolid d…
A Geometric Perspective on the Difficulties of Learning GNN-based SAT Solvers
Geri Skenderi
Graph Neural Networks (GNNs) have gathered increasing interest as learnable solvers of Boolean Satisfiability Problems (SATs), operating on graph representations of logical formula…
Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning
Geri Skenderi, Luigi Capogrosso, Andrea Toaiari +3
Auxiliary tasks facilitate learning in situations where data is scarce or the principal task of interest is extremely complex. This idea is primarily inspired by the improved gener…
Graph-level Representation Learning with Joint-Embedding Predictive Architectures
Geri Skenderi, Hang Li, Jiliang Tang +1
Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-ba…