Graph signal processing is a fast growing field where classical signal processing tools developed in the Euclidean domain have been generalised to irregular domains such as graphs. Below you can find a (non-exhaustive) list of useful resources in the field of graph signal processing.
Conferences/Workshops/Special Issues
Reviews/Tutorials
- Introductory article
- Shuman et al., "The emerging field of signal processing on graphs", IEEE SPM, vol. 30, no. 3, pp. 83-98, May 2013.
- Sandryhaila and Moura, "Discrete signal processing on graphs", IEEE TSP, vol. 61, no. 7, pp. 1644-1656, April 2013.
- Sandryhaila and Moura, "Big data analysis with signal processing on graphs", IEEE SPM, vol. 31, no. 5, pp. 80-90, September 2014.
- Ortega et al., "Graph signal processing", Proceedings of the IEEE, vol. 106, no. 5, pp. 808-828, May 2018.
- Dong et al., "Graph signal processing for machine learning", IEEE SPM, vol. 37, no. 6, pp. 117-127, November 2020.
- Overview talk
- Transform/dictionary design for graph signals
- Vandergheynst and Shuman, "Wavelets on graphs, an introduction", Université de Provence, November 2011.
- Shuman, "Dictionary design for graph signal processing", GSP Workshop 2016.
- Shuman, "Localized spectral graph filter frames", IEEE SPM, vol. 37, no. 6, pp. 43-63, November 2020.
- Topology inference
- Rabbat, "Inferring network structure from indirect observations", GSP Workshop 2016.
- Dong, "Learning graphs from data: A signal processing perspective", GSP Workshop 2017.
- Giannakis et al., "Topology identification and learning over graphs", Proceedings of the IEEE, vol. 106, no. 5, pp. 787-807, May 2018.
- Mateos et al., "Connecting the dots", IEEE SPM, vol. 36, no. 3, pp. 16-43, May 2019.
- Dong et al., "Learning graphs from data", IEEE SPM, vol. 36, no. 3, pp. 44-63, May 2019.
- Graph neural networks
- Ribeiro and Gama, "Graph neural networks", IEEE ICASSP 2020 Tutorial.
- Gama et al., "Graphs, convolutions, and neural networks", IEEE SPM, vol. 37, no. 6, pp. 128-138, November 2020.
- Cheung et al., "Graph signal processing and deep learning", IEEE SPM, vol. 37, no. 6, pp. 139-149, November 2020.
- Application
- Cheung et al., "Graph spectral image processing", Proceedings of the IEEE, vol. 106, no. 5, pp. 907-930, May 2018.
- Huang et al., "A graph signal processing perspective on functional brain imaging", Proceedings of the IEEE, vol. 106, no. 5, pp. 868-885, May 2018.
Toolboxes
Geometric deep learning is a new field where deep learning techniques have been generalised to geometric domains such as graphs and manifolds. As such, it has an intimate relationship with the field of graph signal processing. Below you can find a (non-exhaustive) list of useful resources in the field of geometric deep learning, and more broadly representation learning on graphs and relational reasoning.
Seminars/Reading Groups
Conferences/Workshops
Reviews/Tutorials
- Hamilton et al., "Representation learning on graphs", IEEE Data Engineering Bulletin, vol. 40, no. 3, pp. 42-74, September 2017.
- Chami et al., "Machine learning on graphs", arXiv, May 2020.
- Bronstein et al., "Geometric deep learning", IEEE SPM, vol. 34, no. 4, pp. 18-42, July 2017.
- Battaglia et al., "Relational inductive biases, deep learning, and graph networks", arXiv, June 2018.
- Wu et al., "A comprehensive survey on graph neural networks", arXiv, January 2019.
- Lee et al., "Attention models in graphs", arXiv, July 2018.
- Sun et al., "Adversarial attack and defense on graph data", arXiv, December 2018.
- Jin et al., "Adversarial attacks and defenses on graphs", arXiv, March 2020.
Websites
Toolboxes