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...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awdur:	Pérez Casulo, María Sofía (author)
Awduron Eraill:	Fiori, Marcelo (author), Larroca, Federico (author), Mateos, Gonzalo (author)
Fformat:	article
Iaith:	Saesneg
Cyhoeddwyd:	2025
Pynciau:	Graph Representation Learning Algorithm Unrolling Gradient Descent
Mynediad Ar-lein:	https://openreview.net/forum?id=J65NBLWrmh https://hdl.handle.net/20.500.12008/51328
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!