Skip to Main content Skip to Navigation
Conference papers

Interferometric Graph Transform: a Deep Unsupervised Graph Representation

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.
Complete list of metadata
Contributor : Edouard Oyallon <>
Submitted on : Tuesday, June 9, 2020 - 3:42:01 PM
Last modification on : Tuesday, March 23, 2021 - 9:28:03 AM


Files produced by the author(s)


  • HAL Id : hal-02862516, version 1
  • ARXIV : 2006.05722


Edouard Oyallon. Interferometric Graph Transform: a Deep Unsupervised Graph Representation. 37th International Conference on Machine Learning (ICML 2020), Jul 2020, Online, Austria. ⟨hal-02862516⟩



Record views


Files downloads