Trainable Joint Time-Vertex Fractional Fourier Transform

Abstract

To address limitations of the graph fractional Fourier transform (GFRFT) Wiener filtering and the traditional joint time-vertex fractional Fourier transform (JFRFT) Wiener filtering, this study proposes a filtering method based on the hyper-differential form of the JFRFT. The gradient backpropagation mechanism is employed to enable the adaptive selection of transform order pair and filter coefficients. First, leveraging the hyper-differential form of the GFRFT and the fractional Fourier transform, the hyper-differential form of the JFRFT is constructed and its properties are analyzed. Second, time-varying graph signals are divided into dynamic graph sequences of equal span along the temporal dimension. A spatiotemporal joint representation is then established through vectorized reorganization, followed by the joint time-vertex Wiener filtering. Furthermore, by rigorously proving the differentiability of the transform orders, both the transform orders and filter coefficients are embedded as learnable parameters within a neural network architecture. Through gradient backpropagation, their synchronized iterative optimization is achieved, constructing a parameters-adaptive learning filtering framework. This method leverages a model-driven approach to learn the optimal transform order pair and filter coefficients. Experimental results indicate that the proposed framework improves the time-varying graph signals denoising performance, while reducing the computational burden of the traditional grid search strategy.