LASE : Learned Adjacency Spectral Embeddings

We put forth a principled design of a neural architecture to learn nodal Adjacency Spectral Embeddings (ASE) from graph inputs. By bringing to bear the gradient descent (GD) method and leveraging the technique of algorithm unrolling, we truncate and re-interpret each GD iteration as a layer in a gra...

Full description

Bibliographic Details

Main Author:	Pérez Casulo, María Sofía (author)
Other Authors:	Fiori, Marcelo (author), Larroca, Federico (author), Mateos, Gonzalo (author)
Format:	article
Language:	English
Published:	2025
Subjects:	Graph Representation Learning Algorithm Unrolling Gradient Descent
Online Access:	https://openreview.net/forum?id=J65NBLWrmh https://hdl.handle.net/20.500.12008/51328
Tags:	Add Tag No Tags, Be the first to tag this record!