Extracting learning backbones: a zero-forcing-based approach to graph sparsification for graph classification

Abstract This paper introduces a control-theoretic framework for graph sparsification aimed at constructing sparse subgraphs that retain the learning capacity of the original graph, reducing structural complexity while maintaining downstream performance. We refer to these sparse graphs as learning b...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Obaid Ullah Ahmad, Anwar Said, Xenofon Koutsoukos, Waseem Abbas
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	SpringerOpen 2026-04-01
Цуврал:	Applied Network Science
Нөхцлүүд:	Sparsification Network control backbone Graph neural networks Graph classification
Онлайн хандалт:	https://doi.org/10.1007/s41109-026-00789-0
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!