Important Dates

  • Submission open: February 1, 2023
  • Submission deadline: March 1, 2023 March 15, 2023
  • Notification of acceptance: March 15, 2023 April 1, 2023
  • Early registration: April 1, 2023 April 22, 2023
  • Workshop: June 12-14, 2023


We accept submission of 2-page extended abstracts with standard IEEE or ACM format. Accepted contributions will be arranged in the format of oral or poster presentations. The workshop is a venue to share recent research results with no published proceedings. Authors are encouraged to send previously published papers as extended abstracts. Authors of accepted abstracts who are interested in further advertising their work are welcome to submit their abstract (or the full version of their work) to arXiv with the quote “This work was accepted to be presented at the Graph Signal Processing Workshop 2023”.

Submission is now open here.

If you have any questions regarding submission or enquiries about the workshop, please contact

Area of interest

A graph signal is a signal in which relationships between its components follow the structure encoded in a weighted graph. The purpose of graph signal processing is to exploit this underlying structure to analyze and process graph signals. The last few years have seen significant progress in the development of theory, tools, and applications of graph signal processing, as well as of related fields such as graph machine learning. The Graph Signal Processing Workshop is a forum intended to disseminate ideas to a broader audience and to exchange ideas and experiences on the future path of this vibrant field.

Topics of interest include but are not limited to:

  • Sampling and recovery of graph signals
  • Graph filter and filter bank design
  • Uncertainty principles and other fundamental limits
  • Graph signal transforms
  • Graph filter identification
  • Graph topology inference
  • Statistical graph signal processing
  • Signal processing on higher-order networks
  • Non-linear graph signal processing
  • Prediction and learning in graphs
  • Geometric deep learning (graph CNNs/RNNs)
  • Representation learning on graphs
  • Reinforcement learning on graphs
  • Applications to image and video processing
  • Applications to neuroscience and other medical fields
  • Applications to economics and social networks
  • Applications to infrastructure networks (e.g., communication, transportation, power networks)