Interferometric Graph Transform: a Deep Unsupervised Graph Representation

Edouard Oyallon
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:7434-7444, 2020.

Abstract

We propose the Interferometric Graph Transform (IGT), which is a new class of deep unsupervised graph convolutional neural network for building graph representations. Our first contribution is to propose a generic, complex-valued spectral graph architecture obtained from a generalization of the Euclidean Fourier transform. We show that our learned representation consists of both discriminative and invariant features, thanks to a novel greedy concave objective. From our experiments, we conclude that our learning procedure exploits the topology of the spectral domain, which is normally a flaw of spectral methods, and in particular our method can recover an analytic operator for vision tasks. We test our algorithm on various and challenging tasks such as image classification (MNIST, CIFAR-10), community detection (Authorship, Facebook graph) and action recognition from 3D skeletons videos (SBU, NTU), exhibiting a new state-of-the-art in spectral graph unsupervised settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-oyallon20a, title = {Interferometric Graph Transform: a Deep Unsupervised Graph Representation}, author = {Oyallon, Edouard}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {7434--7444}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/oyallon20a/oyallon20a.pdf}, url = {https://proceedings.mlr.press/v119/oyallon20a.html}, abstract = {We propose the Interferometric Graph Transform (IGT), which is a new class of deep unsupervised graph convolutional neural network for building graph representations. Our first contribution is to propose a generic, complex-valued spectral graph architecture obtained from a generalization of the Euclidean Fourier transform. We show that our learned representation consists of both discriminative and invariant features, thanks to a novel greedy concave objective. From our experiments, we conclude that our learning procedure exploits the topology of the spectral domain, which is normally a flaw of spectral methods, and in particular our method can recover an analytic operator for vision tasks. We test our algorithm on various and challenging tasks such as image classification (MNIST, CIFAR-10), community detection (Authorship, Facebook graph) and action recognition from 3D skeletons videos (SBU, NTU), exhibiting a new state-of-the-art in spectral graph unsupervised settings.} }
Endnote
%0 Conference Paper %T Interferometric Graph Transform: a Deep Unsupervised Graph Representation %A Edouard Oyallon %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-oyallon20a %I PMLR %P 7434--7444 %U https://proceedings.mlr.press/v119/oyallon20a.html %V 119 %X We propose the Interferometric Graph Transform (IGT), which is a new class of deep unsupervised graph convolutional neural network for building graph representations. Our first contribution is to propose a generic, complex-valued spectral graph architecture obtained from a generalization of the Euclidean Fourier transform. We show that our learned representation consists of both discriminative and invariant features, thanks to a novel greedy concave objective. From our experiments, we conclude that our learning procedure exploits the topology of the spectral domain, which is normally a flaw of spectral methods, and in particular our method can recover an analytic operator for vision tasks. We test our algorithm on various and challenging tasks such as image classification (MNIST, CIFAR-10), community detection (Authorship, Facebook graph) and action recognition from 3D skeletons videos (SBU, NTU), exhibiting a new state-of-the-art in spectral graph unsupervised settings.
APA
Oyallon, E.. (2020). Interferometric Graph Transform: a Deep Unsupervised Graph Representation. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:7434-7444 Available from https://proceedings.mlr.press/v119/oyallon20a.html.

Related Material