Context-guided diffusion for label propagation on graphs
This work addresses a bottleneck in graph-based semi-supervised learning for researchers and practitioners by proposing a novel anisotropic approach.
The paper tackles the problem of isotropic diffusion in graph-based label propagation by introducing anisotropic diffusion inspired by image processing, resulting in significantly improved semi-supervised learning performance over existing methods.
Existing approaches for diffusion on graphs, e.g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer. Inspired by the success of diffusivity tensors for anisotropic diffusion in image processing, we presents anisotropic diffusion on graphs and the corresponding label propagation algorithm. We develop positive definite diffusivity operators on the vector bundles of Riemannian manifolds, and discretize them to diffusivity operators on graphs. This enables us to easily define new robust diffusivity operators which significantly improve semi-supervised learning performance over existing diffusion algorithms.