Log In Sign Up

Graphs as Tools to Improve Deep Learning Methods

by   Carlos Lassance, et al.

In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require a lot of training data, which might not be available in some practical applications. In addition, when small perturbations are added to the inputs, DNNs are prone to misclassification errors. DNNs are also viewed as black-boxes and as such their decisions are often criticized for their lack of interpretability. In this chapter, we review recent works that aim at using graphs as tools to improve deep learning methods. These graphs are defined considering a specific layer in a deep learning architecture. Their vertices represent distinct samples, and their edges depend on the similarity of the corresponding intermediate representations. These graphs can then be leveraged using various methodologies, many of which built on top of graph signal processing. This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.


Graphs for deep learning representations

In recent years, Deep Learning methods have achieved state of the art pe...

DeepPINK: reproducible feature selection in deep neural networks

Deep learning has become increasingly popular in both supervised and uns...

Generating Textual Adversarial Examples for Deep Learning Models: A Survey

With the development of high computational devices, deep neural networks...

Representing Deep Neural Networks Latent Space Geometries with Graphs

Deep Learning (DL) has attracted a lot of attention for its ability to r...

Mechanisms of Artistic Creativity in Deep Learning Neural Networks

The generative capabilities of deep learning neural networks (DNNs) have...

Como funciona o Deep Learning

Deep Learning methods are currently the state-of-the-art in many problem...