From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach

no code implementations • 6 Nov 2023 • Tuan Nguyen, Hirotada Honda, Takashi Sano, Vinh Nguyen, Shugo Nakamura, Tan M. Nguyen

We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoothing phenomenon, in which node features in GNNs become indistinguishable as the number of layers increases.

An Analytic Solution to the Inverse Ising Problem in the Tree-reweighted Approximation

no code implementations • 29 May 2018 • Takashi Sano

By solving the moment-matching and self-consistency conditions analytically, we can derive the interaction matrix as a function of the given data statistics.