Learning Regularization for Graph Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eliasof, Moshe, Siddiqui, Md Shahriar Rahim, Schönlieb, Carola-Bibiane, Haber, Eldad
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916648875720704
author Eliasof, Moshe
Siddiqui, Md Shahriar Rahim
Schönlieb, Carola-Bibiane
Haber, Eldad
author_facet Eliasof, Moshe
Siddiqui, Md Shahriar Rahim
Schönlieb, Carola-Bibiane
Haber, Eldad
contents In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks. In many applications, it is impossible to observe some properties of the graph directly; instead, noisy and indirect measurements of these properties are available. These scenarios are coined as Graph Inverse Problems (GRIP). In this work, we introduce a framework leveraging GNNs to solve GRIPs. The framework is based on a combination of likelihood and prior terms, which are used to find a solution that fits the data while adhering to learned prior information. Specifically, we propose to combine recent deep learning techniques that were developed for inverse problems, together with GNN architectures, to formulate and solve GRIP. We study our approach on a number of representative problems that demonstrate the effectiveness of the framework.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10436
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Regularization for Graph Inverse Problems
Eliasof, Moshe
Siddiqui, Md Shahriar Rahim
Schönlieb, Carola-Bibiane
Haber, Eldad
Machine Learning
In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks. In many applications, it is impossible to observe some properties of the graph directly; instead, noisy and indirect measurements of these properties are available. These scenarios are coined as Graph Inverse Problems (GRIP). In this work, we introduce a framework leveraging GNNs to solve GRIPs. The framework is based on a combination of likelihood and prior terms, which are used to find a solution that fits the data while adhering to learned prior information. Specifically, we propose to combine recent deep learning techniques that were developed for inverse problems, together with GNN architectures, to formulate and solve GRIP. We study our approach on a number of representative problems that demonstrate the effectiveness of the framework.
title Learning Regularization for Graph Inverse Problems
topic Machine Learning
url https://arxiv.org/abs/2408.10436