ML Anthology

Understanding Convolutions on Graphs

Ameya Daigavane, Balaraman Ravindran, Gaurav Aggarwal
Distill 2021
doi:10.23915/distill.00032 /distill/2021/daigavane2021distill-understanding/

Abstract

Distill articles are interactive publications and do not include traditional abstracts. This summary was written for the ML Anthology. Explains how convolutions can be extended from regular grids to graph-structured data, introducing polynomial filters, spectral methods, and modern architectures like graph convolutional networks and graph attention networks through interactive visualizations.

Distill Code Semantic Scholar

Cite

Text

Daigavane et al. "Understanding Convolutions on Graphs." Distill, 2021. doi:10.23915/distill.00032

Markdown

[Daigavane et al. "Understanding Convolutions on Graphs." Distill, 2021.](https://mlanthology.org/distill/2021/daigavane2021distill-understanding/) doi:10.23915/distill.00032

BibTeX

@article{daigavane2021distill-understanding,
  title     = {{Understanding Convolutions on Graphs}},
  author    = {Daigavane, Ameya and Ravindran, Balaraman and Aggarwal, Gaurav},
  journal   = {Distill},
  year      = {2021},
  doi       = {10.23915/distill.00032},
  url       = {https://mlanthology.org/distill/2021/daigavane2021distill-understanding/}
}