10 papers
Optimal Sampling and Reconstruction of Graph Signals in the Fractional Fourier Domain
Xiaopeng Cheng, Zhichao Zhang, Yangfan He
Graph signal sampling and reconstruction are commonly formulated in the graph Fourier transform (GFT) domain. However, the reconstruction performance may be limited when practical…
Generalized Linear Graph Representation: A Compact Operator Space for Graph Signal Processing and Graph Neural Networks
Feiyue Zhao, Zhichao Zhang, Yangfan He
Graph Signal Processing (GSP) and Graph Neural Networks (GNNs) rely fundamentally on the matrix representation of the underlying graph topology. This representation defines key ope…
Node-Oriented Proactive Spectral Modulation: A Unified Fractional Framework for Graph Signal Denoising
Manjun Cui, Zhichao Zhang, Yangfan He
Graph signal denoising is a fundamental task in graph signal processing. While the node-oriented filtering approach enhances spatial adaptability, it suffers from spectral rigidity…
A Unified Fractional Spectral Framework for Spatiotemporal Graph Signals: Bi-Fractional Transform and Geodesic Coupling
Mingzhi Wang, Manjun Cui, Feiyue Zhao +2
Graph signal processing extends spectral analysis to data supported on irregular domains. Existing fractional transforms for two-dimensional graph signals, including the two-dimens…
DWAFM: Dynamic Weighted Graph Structure Embedding Integrated with Attention and Frequency-Domain MLPs for Traffic Forecasting
Sen Shi, Zhichao Zhang, Yangfan He
Accurate traffic prediction is a key task for intelligent transportation systems. The core difficulty lies in accurately modeling the complex spatial-temporal dependencies in traff…
FGFRFT: Fast Graph Fractional Fourier Transform via Exact Spectral Splitting and Fourier-Series Approximation
Ziqi Yan, Mingzhi Wang, Sen Shi +4
The graph fractional Fourier transform (GFRFT) for unitary graph Fourier transform (GFT) matrices can be interpreted through the scalar function on the unit circle. Under…
Dynamic Multiple-Parameter Joint Time-Vertex Fractional Fourier Transform and its Intelligent Filtering Methods
Manjun Cui, Ziqi Yan, Yangfan He +1
Dynamic graph signal processing provides a principled framework for analyzing time-varying data defined on irregular graph domains. However, existing joint time-vertex transforms s…
Rotation-Parameterized Graph Fractional Fourier Transform: Definition, Properties, and Optimal Filtering
Feiyue Zhao, Mingzhi Wang, Yangfan He +1
Graph spectral representations are fundamental in graph signal processing, providing a rigorous frameworkforanalyzing graph-structured data. The graph fractional Fourier transform…
MPFSR-Enhanced GNNs: Spectral Graph Neural Networks Enhancement Through Learnable Multiple-Parameter Graph Fractional Fourier Transforms
Manjun Cui, Xiaopeng Cheng, Yangfan He +1
Graph neural networks (GNNs) excel in processing non-Euclidean data, but traditional spectral GNNs rely on static bases and fundamentally lack active spectral regulation. Although…
Least-Squares Adaptive Filter-Based Cohen's Class Time-Frequency Distribution for Signal Denoising
Manjun Cui, Zhichao Zhang, Yangfan He
Inspired by the use of adaptive kernel-based Cohen's class time-frequency distributions (CCTFDs) for cross-term suppression, this paper aims to explore novel adaptive kernel functi…