Learning deep representations by mutual information estimation and maximization

R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, Yoshua Bengio

Abstract: This work investigates unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality in the input into the objective can significantly improve a representation's suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and compares favorably with fully-supervised learning on several classification tasks in with some standard architectures. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation learning objectives for specific end-goals.

Keywords: representation learning, unsupervised learning, deep learning

TL;DR: We learn deep representation by maximizing mutual information, leveraging structure in the objective, and are able to compute with fully supervised classifiers with comparable architectures

Code: [ rdevon/DIM](https://github.com/rdevon/DIM) + [ 8 community implementations](https://paperswithcode.com/paper/?openreview=Bklr3j0cKX)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100), [CelebA](https://paperswithcode.com/dataset/celeba), [STL-10](https://paperswithcode.com/dataset/stl-10)

Community Implementations: [ 9 code implementations](https://www.catalyzex.com/paper/arxiv:1808.06670/code)