Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables

Joo, Weonyoung; Kim, Dong‐Jun; Shin, Seungjae; Moon, Il‐Chul

doi:10.48550/arxiv.2003.01847

Cited by 4 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The activation function used is LeakyReLU. Gumbel Softmax outperforms softmax in terms of discrete text production ( Joo et al, 2020 ). After experimenting with various sequence lengths, it was discovered that sequence length 160 produced the best results.…”

Section: Methodsmentioning

confidence: 99%

Gene Ontology Capsule GAN: an improved architecture for protein function prediction

Mansoor¹,

Nauman²,

Rehman³

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Proteins are the core of all functions pertaining to living things. They consist of an extended amino acid chain folding into a three-dimensional shape that dictates their behavior. Currently, convolutional neural networks (CNNs) have been pivotal in predicting protein functions based on protein sequences. While it is a technology crucial to the niche, the computation cost and translational invariance associated with CNN make it impossible to detect spatial hierarchies between complex and simpler objects. Therefore, this research utilizes capsule networks to capture spatial information as opposed to CNNs. Since capsule networks focus on hierarchical links, they have a lot of potential for solving structural biology challenges. In comparison to the standard CNNs, our results exhibit an improvement in accuracy. Gene Ontology Capsule GAN (GOCAPGAN) achieved an F1 score of 82.6%, a precision score of 90.4% and recall score of 76.1%.

show abstract

Section: Methodsmentioning

confidence: 99%

Gene Ontology Capsule GAN: an improved architecture for protein function prediction

Mansoor¹,

Nauman²,

Rehman³

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…However, directly sampling word counts from the Poisson distribution is not differentiable. In order to enable back-propagation of gradients, we apply Gumbel-Softmax (Jang et al, 2017;Joo et al, 2020), which is a gradient estimator with the reparameterization trick.…”

Section: Distant Supervision and Adversarial Learningmentioning

confidence: 99%

Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews

Runcong¹,

Gui²,

Pergola³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose the Brand-Topic Model (BTM) which aims to detect brandassociated polarity-bearing topics from product reviews. Different from existing models for sentiment-topic extraction which assume topics are grouped under discrete sentiment categories such as 'positive', 'negative' and 'neural', BTM is able to automatically infer real-valued brand-associated sentiment scores and generate fine-grained sentiment-topics in which we can observe continuous changes of words under a certain topic (e.g., 'shaver' or 'cream') while its associated sentiment gradually varies from negative to positive. BTM is built on the Poisson factorisation model with the incorporation of adversarial learning. It has been evaluated on a dataset constructed from Amazon reviews. Experimental results show that BTM outperforms a number of competitive baselines in brand ranking, achieving a better balance of topic coherence and uniqueness, and extracting better-separated polaritybearing topics.

show abstract

“…Since score methods deviate from the orthodox backpropagation procedure [35], we opted for the latter. Recently, Joo et al [16] introduced the Generalized Gumbel-Softmax (GenGS) reparametrization, which can approximate any discrete, non-negative, and finite-mean random variable. They achieve this by truncating its support to a finite number of bins and relaxing the resulting categorical distribution into a continuous form using the Gumbel-Softmax reparametrization [13].…”

Section: Numerical Approximationmentioning

confidence: 99%

Digital Gimbal: End-to-end Deep Image Stabilization with Learnable Exposure Times

Dahary¹,

Jacoby²,

Bronstein³

2020

Preprint

View full text Add to dashboard Cite

Mechanical image stabilization using actuated gimbals enables capturing long-exposure shots without suffering from blur due to camera motion. These devices, however, are often physically cumbersome and expensive, limiting their widespread use. In this work, we propose to digitally emulate a mechanically stabilized system from the input of a fast unstabilized camera. To exploit the trade-off between motion blur at long exposures and low SNR at short exposures, we train a CNN that estimates a sharp high-SNR image by aggregating a burst of noisy short-exposure frames, related by unknown motion. We further suggest learning the burst's exposure times in an end-to-end manner, thus balancing the noise and blur across the frames. We demonstrate this method's advantage over the traditional approach of deblurring a single image or denoising a fixedexposure burst.

show abstract

Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables

Cited by 4 publications

References 4 publications

Gene Ontology Capsule GAN: an improved architecture for protein function prediction

Gene Ontology Capsule GAN: an improved architecture for protein function prediction

Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews

Digital Gimbal: End-to-end Deep Image Stabilization with Learnable Exposure Times

Contact Info

Product

Resources

About