Deep Convolutional Networks on Graph-Structured Data

by   Mikael Henaff, et al.

Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities. In this paper we consider the general question of how to construct deep architectures with small learning complexity on general non-Euclidean domains, which are typically unknown and need to be estimated from the data. In particular, we develop an extension of Spectral Networks which incorporates a Graph Estimation procedure, that we test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.


Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks

Recently, neural network based approaches have achieved significant impr...

An attention-driven hierarchical multi-scale representation for visual recognition

Convolutional Neural Networks (CNNs) have revolutionized the understandi...

LanczosNet: Multi-Scale Deep Graph Convolutional Networks

We propose the Lanczos network (LanczosNet), which uses the Lanczos algo...

Higher-order Graph Convolutional Networks

Following the success of deep convolutional networks in various vision a...

A Review of Graph Neural Networks and Their Applications in Power Systems

Deep neural networks have revolutionized many machine learning tasks in ...

Spectral Networks and Locally Connected Networks on Graphs

Convolutional Neural Networks are extremely efficient architectures in i...

Understanding Deep Convolutional Networks through Gestalt Theory

The superior performance of deep convolutional networks over high-dimens...

Code Repositories