paper-with-me

홈 › Papers

Learning deep representations by mutual information estimation and maximization

2018-08-20 · ICLR 2019 5 · R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, Yoshua Bengio

In this work, we perform 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 of the input to the objective can greatly influence 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 competes with fully-supervised learning on several classification tasks. 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.

📄 PDF Abstract BibTeX arXiv:1808.06670

Code (8)

rdevon/DIM 공식 구현 pytorch
DuaneNielsen/DeepInfomaxPytorch pytorch
HolenYHR/Deepinfo_pytorch pytorch
bojone/infomax tf
createamind/DIM_Commented pytorch
ifding/simple-Infomax-pytorch pytorch
jqhoogland/rgpy tf
schzhu/learning-adversarially-robust-representations pytorch

Tasks

General ClassificationMutual Information EstimationRepresentation Learning

Similar Papers 제목 키워드 기반

Multimodal Representation Learning via Maximization of Local Mutual Information

2021-03-08 · Ruizhi Liao, Daniel Moyer, Miriam Cha, Keegan Quigley 외

We propose and demonstrate a representation learning approach by maximizing the mutual information between local features of images and text. The goal of this approach is to learn useful image representations by taking a…

image-classificationImage ClassificationMutual Information EstimationRepresentation Learning

Learning Disentangled Representations via Mutual Information Estimation

2019-12-09 · ECCV 2020 8 · Eduardo Hugo Sanchez, Mathieu Serrurier, Mathias Ortner

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a share…

DisentanglementGeneral Classificationimage-classificationImage Classification+5

Multimodal Representations Learning Based on Mutual Information Maximization and Minimization and Identity Embedding for Multimodal Sentiment Analysis

2022-01-10 · Jiahao Zheng, Sen Zhang, XiaoPing Wang, Zhigang Zeng

Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression. Although there have been many succe…

Multimodal Sentiment AnalysisSentiment Analysis

VMI-VAE: Variational Mutual Information Maximization Framework for VAE With Discrete and Continuous Priors

2020-05-28 · Andriy Serdega, Dae-shik Kim

Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned …

Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations

2021-05-14 · Xiaolong Fan, Maoguo Gong, Yue Wu, Hao Li

Recently, maximizing mutual information has emerged as a powerful method for unsupervised graph representation learning. The existing methods are typically effective to capture information from the topology view but igno…

DiversityGraph Representation LearningLinear evaluationRepresentation Learning