13 papers
Structured Sheaf Learning of Consistent Connection Graphs
Leonardo Di Nino, Gabriele D'Acunto, Sergio Barbarossa +1
Connection graphs (CGs) extend classical graphs by associating vector-valued signals to nodes and orthogonal transport maps across edges, making them a natural model for synchroniz…
Sheaf-Based Federated Representation Learning
Gabriele D'Acunto, Enrico Grimaldi, Valeria Avino +4
Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures,…
Sheaf-theoretic Signal Processing on Graphs: Spectral Theory, Filtering, and Sampling
Gabriele D'Acunto, Leonardo Di Nino, Paolo Di Lorenzo +1
Modern sensing, communication, and learning systems generate heterogeneous network signals, with local data differing in dimension, modality, and geometric structure. Processing su…
A Sheaf-Theoretic Framework for Distributed Multi-Site Channel Charting
Enrico Grimaldi, Leonardo Di Nino, Mario Edoardo Pandolfo +3
Channel charting (CC) enables data-driven user localization in wireless networks by embedding channel state information (CSI) into low-dimensional representations. In multi-cell sc…
Learning Dirac Spectral Transforms for Topological Signals
Leonardo Di Nino, Tiziana Cattai, Sergio Barbarossa +2
The Dirac operator provides a unified framework for processing signals defined over different order topological domains, such as node and edge signals. Its eigenmodes define a spec…
SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations
Mario Edoardo Pandolfo, Enrico Grimaldi, Lorenzo Marinucci +4
Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, compar…