2023/10/09 by Yixuan He, He, Yixuan, Gesine Reinert +5
Computer Science · #Blind Source Separation Techniques #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Neural Networks and Reservoir Computing #Optimization and Control (math.OC)
paper · pdf · doi:10.48550/arxiv.2310.05842
openalex publication_date 2023/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The angular synchronization problem aims to accurately estimate (up to a constant additive phase) a set of unknown angles θ1, …, θn∈[0, 2π) from m noisy measurements of their offsets θi-θj 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.