Robust Angular Synchronization via Directed Graph Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Yixuan, Reinert, Gesine, Wipf, David, Cucuringu, Mihai
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929241010995200
author He, Yixuan
Reinert, Gesine
Wipf, David
Cucuringu, Mihai
author_facet He, Yixuan
Reinert, Gesine
Wipf, David
Cucuringu, Mihai
contents The angular synchronization problem aims to accurately estimate (up to a constant additive phase) a set of unknown angles $θ_1, \dots, θ_n\in[0, 2π)$ from $m$ noisy measurements of their offsets $θ_i-θ_j \;\mbox{mod} \; 2π.$ Applications include, for example, sensor network localization, phase retrieval, and distributed clock synchronization. An extension of the problem to the heterogeneous setting (dubbed $k$-synchronization) is to estimate $k$ groups of angles simultaneously, given noisy observations (with unknown group assignment) from each group. Existing methods for angular synchronization usually perform poorly in high-noise regimes, which are common in applications. In this paper, we leverage neural networks for the angular synchronization problem, and its heterogeneous extension, by proposing GNNSync, a theoretically-grounded end-to-end trainable framework using directed graph neural networks. In addition, new loss functions are devised to encode synchronization objectives. Experimental results on extensive data sets demonstrate that GNNSync attains competitive, and often superior, performance against a comprehensive set of baselines for the angular synchronization problem and its extension, validating the robustness of GNNSync even at high noise levels.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05842
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Robust Angular Synchronization via Directed Graph Neural Networks
He, Yixuan
Reinert, Gesine
Wipf, David
Cucuringu, Mihai
Machine Learning
Optimization and Control
The angular synchronization problem aims to accurately estimate (up to a constant additive phase) a set of unknown angles $θ_1, \dots, θ_n\in[0, 2π)$ from $m$ noisy measurements of their offsets $θ_i-θ_j \;\mbox{mod} \; 2π.$ Applications include, for example, sensor network localization, phase retrieval, and distributed clock synchronization. An extension of the problem to the heterogeneous setting (dubbed $k$-synchronization) is to estimate $k$ groups of angles simultaneously, given noisy observations (with unknown group assignment) from each group. Existing methods for angular synchronization usually perform poorly in high-noise regimes, which are common in applications. In this paper, we leverage neural networks for the angular synchronization problem, and its heterogeneous extension, by proposing GNNSync, a theoretically-grounded end-to-end trainable framework using directed graph neural networks. In addition, new loss functions are devised to encode synchronization objectives. Experimental results on extensive data sets demonstrate that GNNSync attains competitive, and often superior, performance against a comprehensive set of baselines for the angular synchronization problem and its extension, validating the robustness of GNNSync even at high noise levels.
title Robust Angular Synchronization via Directed Graph Neural Networks
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2310.05842