Xiaosheng Zhuang

Nira Dyn, Xiaosheng Zhuang

Multiscale transforms for real-valued data, based on interpolatory subdivision operators have been studied in recent year. They are easy to define, and can be extended to other types of data, for example to manifold-valued data. In this paper we define linear multiscale transforms, based on certain linear, non-interpolatory subdivision operators, termed "even-reversible". For such operators, we prove, using Wiener's lemma, the existence of an inverse to the linear operator defined by the even part of the subdivision mask, and termed it "even-inverse". We show that the non-interpolatory subdivision operators, with spline or with pseudo-spline masks, are even-reversible, and derive explicitly, for the quadratic and cubic spline subdivision operators, the symbols of the corresponding even-inverse operators. We also analyze properties of the multiscale transforms based on even-reversible subdivision operators, in particular, their stability and the rate of decay of the details.

Ruigang Zheng, Xiaosheng Zhuang

In this paper, we propose a general framework for constructing tight framelet systems on graphs with localized supports based on partition trees. Our construction of framelets provides a simple and efficient way to obtain the orthogonality with $k$ arbitrary orthonormal vectors. When the $k$ vectors contain most of the energy of a family of graph signals, the orthogonality of the framelets intuitively possesses ``generalized ($k$-)vanishing'' moments, and thus, the coefficients are sparse. Moreover, our construction provides not only framelets that are overall sparse vectors but also fast and schematically concise transforms. In a data-adaptive setting, the graph framelet systems can be learned by conducting optimizations on Stiefel manifolds to provide the utmost sparsity for a given family of graph signals. Furthermore, we further exploit the generality of our proposed graph framelet systems for heterophilous graph learning, where graphs are characterized by connecting nodes mainly from different classes. The usual assumption that connected nodes are similar and belong to the same class for homophilious graphs is contradictory for heterophilous graphs. Thus, we are motivated to bypass simple assumptions on heterophilous graphs and focus on generating rich node features induced by the graph structure, so as to improve the graph learning ability of certain neural networks in node classification. We derive a specific system of graph framelets and propose a heuristic method to select framelets as features for neural network input. Several experiments demonstrate the effectiveness and superiority of our approach for non-linear approximation, denoising, and node classification.

Guangrui Yang, Ming Li, Han Feng et al.

Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their essential ability from a theoretical perspective. Existing theoretical research has primarily focused on the analysis of single-layer GCNs, while a comprehensive theoretical exploration of the stability and generalization of deep GCNs remains limited. In this paper, we bridge this gap by delving into the stability and generalization properties of deep GCNs, aiming to provide valuable insights by characterizing rigorously the associated upper bounds. Our theoretical results reveal that the stability and generalization of deep GCNs are influenced by certain key factors, such as the maximum absolute eigenvalue of the graph filter operators and the depth of the network. Our theoretical studies contribute to a deeper understanding of the stability and generalization properties of deep GCNs, potentially paving the way for developing more reliable and well-performing models.

Jianfei Li, Han Feng, Xiaosheng Zhuang

In this paper, we develop a general theoretical framework for constructing Haar-type tight framelets on any compact set with a hierarchical partition. In particular, we construct a novel area-regular hierarchical partition on the 2-sphere and establish its corresponding spherical Haar tight framelets with directionality. We conclude by evaluating and illustrating the effectiveness of our area-regular spherical Haar tight framelets in several denoising experiments. Furthermore, we propose a convolutional neural network (CNN) model for spherical signal denoising which employs the fast framelet decomposition and reconstruction algorithms. Experiment results show that our proposed CNN model outperforms threshold methods, and processes strong generalization and robustness properties.