Data-Adaptive Graph Framelets with Generalized Vanishing Moments for Graph Signal Processing
In this paper, we propose a novel and general framework to construct tight framelet systems on graphs with localized supports based on hierarchical partitions. Our construction provides parametrized graph framelet systems with great generality based on partition trees, by which we are able to find the size of a low-dimensional subspace that best fits the low-rank structure of a family of signals. The orthogonal decomposition of subspaces provides a key ingredient for the definition of "generalized vanishing moments" for graph framelets. In a data-adaptive setting, the graph framelet systems can be learned by solving an optimization problem on Stiefel manifolds with respect to our parameterization. Moreover, such graph framelet systems can be further improved by solving a subsequent optimization problem on Stiefel manifolds, aiming at providing the utmost sparsity for a given family of graph signals. Experimental results show that our learned graph framelet systems perform superiorly in non-linear approximation and denoising tasks.
Code (1)
Tasks
DenoisingSimilar Papers 제목 키워드 기반
Adaptive directional Haar tight framelets on bounded domains for digraph signal representations
Based on hierarchical partitions, we provide the construction of Haar-type tight framelets on any compact set $K\subseteq \mathbb{R}^d$. In particular, on the unit block $[0,1]^d$, such tight framelets can be built to be…
A structural characterization of Compactly Supported OEP-based balanced dual multiframelets
Compared to scalar framelets, multiframelets have certain advantages, such as relatively smaller supports on generators, high vanishing moments, etc. The balancing property of multiframelets is very desired, as it reflec…
Generalized energy and gradient flow via graph framelets
In this work, we provide a theoretical understanding of the framelet-based graph neural networks through the perspective of energy gradient flow. By viewing the framelet-based models as discretized gradient flows of some…
Graph Neural NetworkPermutation Equivariant Graph Framelets for Heterophilous Graph Learning
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregations beyond the 1-hop neighborhood. In th…
Graph LearningGraph Neural NetworkDecimated Framelet System on Graphs and Fast G-Framelet Transforms
Graph representation learning has many real-world applications, from super-resolution imaging, 3D computer vision to drug repurposing, protein classification, social networks analysis. An adequate representation of graph…
Graph ClassificationGraph Representation LearningRepresentation LearningSuper-Resolution