5 papers
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou, Juan Cervino, Pascal Frossard +7
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…
Cross-Learning from Scarce Data via Multi-Task Constrained Optimization
Leopoldo Agorio, Juan Cerviño, Miguel Calvo-Fullana +2
A learning task, understood as the problem of fitting a parametric model from supervised data, fundamentally requires the dataset to be large enough to be representative of the und…
Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
In this paper, we study the generalization capabilities of geometric graph neural networks (GNNs). We consider GNNs over a geometric graph constructed from a finite set of randomly…
A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
Graph Neural Networks (GNNs) extend convolutional neural networks to operate on graphs. Despite their impressive performances in various graph learning tasks, the theoretical under…
Constrained Learning for Decentralized Multi-Objective Coverage Control
Juan Cervino, Saurav Agarwal, Vijay Kumar +1
The multi-objective coverage control problem requires a robot swarm to collaboratively provide sensor coverage to multiple heterogeneous importance density fields IDFs simultaneous…