Preconditioned Diffusion Multitask Clustering Graph Filters

Abstract

In this work, we are interested in the design of node-variant FIR graph filters, in which the graph filter estimates the filter coefficients from the stream data. Considering the estimation of filter coefficients as a task, we introduce concept of the multitask into graph filters. The filter coefficients can be divided into different clusters, and the cooperation between clusters is beneficial. Then, a multitask graph diffusion LMS algorithm is proposed. In order to improve convergence speed and performance, a multitask graph diffusion preconditioned algorithm is proposed. The simulation results verify the feasibility of algorithms.