scholarly journals Robust Data Programming with Precision-guided Labeling Functions

2020 ◽  
Vol 34 (04) ◽  
pp. 3397-3404 ◽  
Author(s):  
Oishik Chatterjee ◽  
Ganesh Ramakrishnan ◽  
Sunita Sarawagi
Keyword(s):  
Generative Models ◽  
Generative Model ◽  
Learning Models ◽  
Training Process ◽  
Programming Paradigm ◽  
Learning Rates ◽  
Elegant Method ◽  
Accuracy Constraints ◽  
Existing Data ◽  
Noisy Labels

Scarcity of labeled data is a bottleneck for supervised learning models. A paradigm that has evolved for dealing with this problem is data programming. An existing data programming paradigm allows human supervision to be provided as a set of discrete labeling functions (LF) that output possibly noisy labels to input instances and a generative model for consolidating the weak labels. We enhance and generalize this paradigm by supporting functions that output a continuous score (instead of a hard label) that noisily correlates with labels. We show across five applications that continuous LFs are more natural to program and lead to improved recall. We also show that accuracy of existing generative models is unstable with respect to initialization, training epochs, and learning rates. We give control to the data programmer to guide the training process by providing intuitive quality guides with each LF. We propose an elegant method of incorporating these guides into the generative model. Our overall method, called CAGE, makes the data programming paradigm more reliable than other tricks based on initialization, sign-penalties, or soft-accuracy constraints.

scholarly journals Dynamics of Fourier Modes in Torus Generative Adversarial Networks

Mathematics ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 325
Author(s):  
Ángel González-Prieto ◽  
Alberto Mozo ◽  
Edgar Talavera ◽  
Sandra Gómez-Canaval
Keyword(s):  
Fourier Series ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
Training Process ◽  
Small Perturbations ◽  
Adversarial Networks ◽  
Novel Method ◽  
Truncated Fourier Series ◽  
Real Flow ◽  
Machine Learning Models

Generative Adversarial Networks (GANs) are powerful machine learning models capable of generating fully synthetic samples of a desired phenomenon with a high resolution. Despite their success, the training process of a GAN is highly unstable, and typically, it is necessary to implement several accessory heuristics to the networks to reach acceptable convergence of the model. In this paper, we introduce a novel method to analyze the convergence and stability in the training of generative adversarial networks. For this purpose, we propose to decompose the objective function of the adversary min–max game defining a periodic GAN into its Fourier series. By studying the dynamics of the truncated Fourier series for the continuous alternating gradient descend algorithm, we are able to approximate the real flow and to identify the main features of the convergence of GAN. This approach is confirmed empirically by studying the training flow in a 2-parametric GAN, aiming to generate an unknown exponential distribution. As a by-product, we show that convergent orbits in GANs are small perturbations of periodic orbits so the Nash equillibria are spiral attractors. This theoretically justifies the slow and unstable training observed in GANs.

Equivariant Adversarial Network for Image-to-image Translation

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-14
Author(s):  
Masoumeh Zareapoor ◽  
Jie Yang
Keyword(s):  
State Of The Art ◽  
Generative Models ◽  
Generative Model ◽  
Target Domain ◽  
Adversarial Network ◽  
Proposed Model ◽  
Image Translation ◽  
Great Performance ◽  
Representative Model ◽  
The Ideal

Image-to-Image translation aims to learn an image from a source domain to a target domain. However, there are three main challenges, such as lack of paired datasets, multimodality, and diversity, that are associated with these problems and need to be dealt with. Convolutional neural networks (CNNs), despite of having great performance in many computer vision tasks, they fail to detect the hierarchy of spatial relationships between different parts of an object and thus do not form the ideal representative model we look for. This article presents a new variation of generative models that aims to remedy this problem. We use a trainable transformer, which explicitly allows the spatial manipulation of data within training. This differentiable module can be augmented into the convolutional layers in the generative model, and it allows to freely alter the generated distributions for image-to-image translation. To reap the benefits of proposed module into generative model, our architecture incorporates a new loss function to facilitate an effective end-to-end generative learning for image-to-image translation. The proposed model is evaluated through comprehensive experiments on image synthesizing and image-to-image translation, along with comparisons with several state-of-the-art algorithms.

scholarly journals Study on Human Activity Recognition Using Semi-Supervised Active Transfer Learning

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2760
Author(s):  
Seungmin Oh ◽  
Akm Ashiquzzaman ◽  
Dongsu Lee ◽  
Yeonggwang Kim ◽  
Jinsul Kim
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Random Sampling ◽  
Data Gathering ◽  
Human Activity Recognition ◽  
Learning Models ◽  
Active Transfer ◽  
Existing Data

In recent years, various studies have begun to use deep learning models to conduct research in the field of human activity recognition (HAR). However, there has been a severe lag in the absolute development of such models since training deep learning models require a lot of labeled data. In fields such as HAR, it is difficult to collect data and there are high costs and efforts involved in manual labeling. The existing methods rely heavily on manual data collection and proper labeling of the data, which is done by human administrators. This often results in the data gathering process often being slow and prone to human-biased labeling. To address these problems, we proposed a new solution for the existing data gathering methods by reducing the labeling tasks conducted on new data based by using the data learned through the semi-supervised active transfer learning method. This method achieved 95.9% performance while also reducing labeling compared to the random sampling or active transfer learning methods.

scholarly journals Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES

2021 ◽  
Author(s):  
AkshatKumar Nigam ◽  
Robert Pollice ◽  
Mario Krenn ◽  
Gabriel dos Passos Gomes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Deep Learning ◽  
Virtual Screening ◽  
Chemical Space ◽  
Generative Models ◽  
Inverse Design ◽  
Learning Models ◽  
Structure Modification ◽  
Design Models ◽  
Comparable Performance ◽  
And Training

Inverse design allows the design of molecules with desirable properties using property optimization. Deep generative models have recently been applied to tackle inverse design, as they possess the ability to optimize molecular properties directly through structure modification using gradients. While the ability to carry out direct property optimizations is promising, the use of generative deep learning models to solve practical problems requires large amounts of data and is very time-consuming. In this work, we propose STONED – a simple and efficient algorithm to perform interpolation and exploration in the chemical space, comparable to deep generative models. STONED bypasses the need for large amounts of data and training times by using string modifications in the SELFIES molecular representation. We achieve comparable performance on typical benchmarks without any training. We demonstrate applications in high-throughput virtual screening for the design of drugs, photovoltaics, and the construction of chemical paths, allowing for both property and structure-based interpolation in the chemical space. We anticipate our results to be a stepping stone for developing more sophisticated inverse design models and benchmarking tools, ultimately helping generative models achieve wide adoption.

scholarly journals Monte Carlo and Reconstruction Membership Inference Attacks against Generative Models

2019 ◽  
Vol 2019 (4) ◽  
pp. 232-249 ◽  
Author(s):  
Benjamin Hilprecht ◽  
Martin Härterich ◽  
Daniel Bernau
Keyword(s):  
Data Privacy ◽  
Information Leakage ◽  
Generative Models ◽  
Generative Model ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Success Rates ◽  
Model Quality ◽  
Type Formalization

Abstract We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative model. Contrary to previous evaluation metrics for generative models, like Kernel Density Estimation, it only considers samples of the model which are close to training data records. The second attack specifically targets Variational Autoencoders, achieving high membership inference accuracy. Furthermore, previous work mostly considers membership inference adversaries who perform single record membership inference. We argue for considering regulatory actors who perform set membership inference to identify the use of specific datasets for training. The attacks are evaluated on two generative model architectures, Generative Adversarial Networks (GANs) and Variational Autoen-coders (VAEs), trained on standard image datasets. Our results show that the two attacks yield success rates superior to previous work on most data sets while at the same time having only very mild assumptions. We envision the two attacks in combination with the membership inference attack type formalization as especially useful. For example, to enforce data privacy standards and automatically assessing model quality in machine learning as a service setups. In practice, our work motivates the use of GANs since they prove less vulnerable against information leakage attacks while producing detailed samples.

scholarly journals Towards Consistent Variational Auto-Encoding (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13869-13870
Author(s):  
Yijing Liu ◽  
Shuyu Lin ◽  
Ronald Clark
Keyword(s):  
Original Data ◽  
Generative Models ◽  
Generative Model ◽  
Approximate Inference ◽  
Inference Model ◽  
Approach To Learning ◽  
Successful Approach ◽  
Data Point ◽  
Reconstructed Data

Variational autoencoders (VAEs) have been a successful approach to learning meaningful representations of data in an unsupervised manner. However, suboptimal representations are often learned because the approximate inference model fails to match the true posterior of the generative model, i.e. an inconsistency exists between the learnt inference and generative models. In this paper, we introduce a novel consistency loss that directly requires the encoding of the reconstructed data point to match the encoding of the original data, leading to better representations. Through experiments on MNIST and Fashion MNIST, we demonstrate the existence of the inconsistency in VAE learning and that our method can effectively reduce such inconsistency.

scholarly journals Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation

2019 ◽  
Vol 33 ◽  
pp. 6698-6705
Author(s):  
Juntao Li ◽  
Lisong Qiu ◽  
Bo Tang ◽  
Dongmin Chen ◽  
Dongyan Zhao ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Network Models ◽  
Generative Models ◽  
Training Data ◽  
Insufficient Data ◽  
Dialogue System ◽  
Neural Network Models ◽  
Augmentation Techniques ◽  
Training Pair ◽  
Existing Data

Recent successes of open-domain dialogue generation mainly rely on the advances of deep neural networks. The effectiveness of deep neural network models depends on the amount of training data. As it is laboursome and expensive to acquire a huge amount of data in most scenarios, how to effectively utilize existing data is the crux of this issue. In this paper, we use data augmentation techniques to improve the performance of neural dialogue models on the condition of insufficient data. Specifically, we propose a novel generative model to augment existing data, where the conditional variational autoencoder (CVAE) is employed as the generator to output more training data with diversified expressions. To improve the correlation of each augmented training pair, we design a discriminator with adversarial training to supervise the augmentation process. Moreover, we thoroughly investigate various data augmentation schemes for neural dialogue system with generative models, both GAN and CVAE. Experimental results on two open corpora, Weibo and Twitter, demonstrate the superiority of our proposed data augmentation model.

scholarly journals Deep Generative Models Enable Navigation in Sparsely Populated Chemical Space

2021 ◽  
Author(s):  
Michael A. Skinnider ◽  
R. Greg Stacey ◽  
David S. Wishart ◽  
Leonard J. Foster
Keyword(s):  
Chemical Space ◽  
Model Development ◽  
Biological Properties ◽  
Generative Models ◽  
Learning Models ◽  
Model Quality ◽  
Chemical Structures ◽  
On Demand ◽  
Physical Chemical

Deep generative models are powerful tools for the exploration of chemical space, enabling the on-demand gener- ation of molecules with desired physical, chemical, or biological properties. However, these models are typically thought to require training datasets comprising hundreds of thousands, or even millions, of molecules. This per- ception limits the application of deep generative models in regions of chemical space populated by only a small number of examples. Here, we systematically evaluate and optimize generative models of molecules for low-data settings. We carry out a series of systematic benchmarks, training more than 5,000 deep generative models and evaluating over 2.6 billion generated molecules. We find that robust models can be learned from far fewer examples than has been widely assumed. We further identify strategies that dramatically reduce the number of molecules required to learn a model of equivalent quality, and demonstrate the application of these principles by learning models of chemical structures found in bacterial, plant, and fungal metabolomes. The structure of our experiments also allows us to benchmark the metrics used to evaluate generative models themselves. We find that many of the most widely used metrics in the field fail to capture model quality, but identify a subset of well-behaved metrics that provide a sound basis for model development. Collectively, our work provides a foundation for directly learning generative models in sparsely populated regions of chemical space.

scholarly journals Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian deep learning

2021 ◽  
Vol 118 (16) ◽  
pp. e2020324118
Author(s):  
Biwei Dai ◽  
Uroš Seljak
Keyword(s):  
Dark Matter ◽  
Deep Learning ◽  
Generative Models ◽  
Generative Model ◽  
Effective Theory ◽  
High Dimensions ◽  
Wide Range ◽  
Hydrodynamical Simulations ◽  
Physical Laws ◽  
Very High

The goal of generative models is to learn the intricate relations between the data to create new simulated data, but current approaches fail in very high dimensions. When the true data-generating process is based on physical processes, these impose symmetries and constraints, and the generative model can be created by learning an effective description of the underlying physics, which enables scaling of the generative model to very high dimensions. In this work, we propose Lagrangian deep learning (LDL) for this purpose, applying it to learn outputs of cosmological hydrodynamical simulations. The model uses layers of Lagrangian displacements of particles describing the observables to learn the effective physical laws. The displacements are modeled as the gradient of an effective potential, which explicitly satisfies the translational and rotational invariance. The total number of learned parameters is only of order 10, and they can be viewed as effective theory parameters. We combine N-body solver fast particle mesh (FastPM) with LDL and apply it to a wide range of cosmological outputs, from the dark matter to the stellar maps, gas density, and temperature. The computational cost of LDL is nearly four orders of magnitude lower than that of the full hydrodynamical simulations, yet it outperforms them at the same resolution. We achieve this with only of order 10 layers from the initial conditions to the final output, in contrast to typical cosmological simulations with thousands of time steps. This opens up the possibility of analyzing cosmological observations entirely within this framework, without the need for large dark-matter simulations.

scholarly journals G2Basy: A framework to improve the RNN language model and ease overfitting problem

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249820
Author(s):  
Lu Yuwen ◽  
Shuyu Chen ◽  
Xiaohan Yuan
Keyword(s):  
Language Model ◽  
Word Embedding ◽  
Language Models ◽  
Batch Size ◽  
Training Process ◽  
Improve Performance ◽  
Step Size ◽  
Learning Rates ◽  
Speed Up ◽  
Overfitting Problem

Recurrent neural networks are efficient ways of training language models, and various RNN networks have been proposed to improve performance. However, with the increase of network scales, the overfitting problem becomes more urgent. In this paper, we propose a framework—G2Basy—to speed up the training process and ease the overfitting problem. Instead of using predefined hyperparameters, we devise a gradient increasing and decreasing technique that changes the parameters training batch size and input dropout simultaneously by a user-defined step size. Together with a pretrained word embedding initialization procedure and the introduction of different optimizers at different learning rates, our framework speeds up the training process dramatically and improves performance compared with a benchmark model of the same scale. For the word embedding initialization, we propose the concept of “artificial features” to describe the characteristics of the obtained word embeddings. We experiment on two of the most often used corpora—the Penn Treebank and WikiText-2 datasets—and both outperform the benchmark results and show potential towards further improvement. Furthermore, our framework shows better results with the larger and more complicated WikiText-2 corpus than with the Penn Treebank. Compared with other state-of-the-art results, we achieve comparable results with network scales hundreds of times smaller and within fewer training epochs.

Sign in / Sign up

Export Citation Format

Share Document