Geometric Scattering for Graph Data Analysis

Feng Gao, Guy Wolf, Matthew Hirn
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:2122-2131, 2019.

Abstract

We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to retain informative variability and relations in the data (e.g., between individual graphs, or in aggregate), while relating our construction to previous theoretical results that establish the stability of similar transforms to families of graph deformations. We demonstrate the application of our geometric scattering features in graph classification of social network data, and in data exploration of biochemistry data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-gao19e, title = {Geometric Scattering for Graph Data Analysis}, author = {Gao, Feng and Wolf, Guy and Hirn, Matthew}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {2122--2131}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/gao19e/gao19e.pdf}, url = {https://proceedings.mlr.press/v97/gao19e.html}, abstract = {We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to retain informative variability and relations in the data (e.g., between individual graphs, or in aggregate), while relating our construction to previous theoretical results that establish the stability of similar transforms to families of graph deformations. We demonstrate the application of our geometric scattering features in graph classification of social network data, and in data exploration of biochemistry data.} }
Endnote
%0 Conference Paper %T Geometric Scattering for Graph Data Analysis %A Feng Gao %A Guy Wolf %A Matthew Hirn %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-gao19e %I PMLR %P 2122--2131 %U https://proceedings.mlr.press/v97/gao19e.html %V 97 %X We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to retain informative variability and relations in the data (e.g., between individual graphs, or in aggregate), while relating our construction to previous theoretical results that establish the stability of similar transforms to families of graph deformations. We demonstrate the application of our geometric scattering features in graph classification of social network data, and in data exploration of biochemistry data.
APA
Gao, F., Wolf, G. & Hirn, M.. (2019). Geometric Scattering for Graph Data Analysis. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:2122-2131 Available from https://proceedings.mlr.press/v97/gao19e.html.

Related Material