Graph Signal Processing: Distributed Graph Filters

Share

One of the cornerstones of the field of graph signal processing are graph filters, direct analogues of time-domain filters, but intended for signals defined on graphs. In this talk, we give an overview of the graph filtering problem. More specifically, we look at the family of finite impulse response (FIR) and infinite impulse response (IIR) graph filters and show how they can be implemented in a distributed manner. To further limit the communication and computational complexity, we also generalize the state-of-the-art distributed graph filters to filters whose weights show a dependency on the nodes sharing information. These so-called edge-variant graph filters yield significant benefits in terms of filter order reduction thereby leading to amenable communication and complexity savings. The analytical and numerical results presented in this paper illustrate the potential and benefits of this general family of edge-variant graph filters.



  Date and Time

  Location

  Contact

  Registration



  • University of Rochester
  • Rochester, New York
  • United States
  • Building: Wegmans Hall
  • Room Number: 1400

Staticmap?size=250x200&sensor=false&zoom=14&markers=43.1576983%2c 77
  • Zhiyao Duan

  • Starts 19 September 2018 06:33 PM
  • Ends 07 November 2018 06:33 PM
  • All times are America/New_York
  • No Admission Charge
  • Register


  Speakers

Geert Leus

Geert Leus

Topic:

Graph Signal Processing: Distributed Graph Filters

One of the cornerstones of the field of graph signal processing are graph filters, direct analogues of time-domain filters, but intended for signals defined on graphs. In this talk, we give an overview of the graph filtering problem. More specifically, we look at the family of finite impulse response (FIR) and infinite impulse response (IIR) graph filters and show how they can be implemented in a distributed manner. To further limit the communication and computational complexity, we also generalize the state-of-the-art distributed graph filters to filters whose weights show a dependency on the nodes sharing information. These so-called edge-variant graph filters yield significant benefits in terms of filter order reduction thereby leading to amenable communication and complexity savings. The analytical and numerical results presented in this paper illustrate the potential and benefits of this general family of edge-variant graph filters.