Adversarial Feature Matching for Text Generation

Zhang, Yizhe; Gan, Zhe; Fan, Kai; Chen, Zhi; Henao, Ricardo; Shen, Dinghan; Carin, Lawrence

doi:10.48550/arxiv.1706.03850

Cited by 35 publications

(42 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the generator model, to learn the distribution of the generator p g over data x, a prior on input noise variable p z (z) must be defined. This mapping is represented as G(z; θ g ), where G is a [163] [17, 27, 67, 126, 80, 87, 95] Wasserstein GANs with Gradient Penalty (WGAN-GP) [168] [42, 63, 106, 102] Variational Auetoencoder GANs (VAE-GAN) [169] [19, 20, 98, 101] Cycle-GAN [170] [117, 48, 124, 137] Auxiliary GANs (AC-GAN) [171] [116, 118, 140] Progressive Growing GANs (PG-GAN) [172] [116, 138] Orthogonal GAN (O-GAN) [173] [29, 71] Adversarial AutoEncoders (AAE) [174] [132] Balancing GANs (BGAN) [175] [116] Energy-Based GANs (EBGAN) [176] [56] Dual Discriminator GANs (D2GAN) [177] [124] GANs with Quadratic Potential (GAN-QP) [178] [71] One-Class GAN (OCGAN) [179] [89] Patch GANs (PatchGAN) [180] [41] Relativistic Discriminator GANs (RaSGAN) [181] [82] Sequence GANs (SeqGAN) [182] [121] Text GANs (TextGAN) [183] [68]…”

Section: Standard Generative Adversarial Network (Gan)mentioning

confidence: 99%

“…Its single scalar output represents the probability that x comes from the data rather than p The Standard GAN optimizes the Jensen-Shannon (JS) divergence to learn the distribution of the data. Consequently, it suffers from an unstable, weak signal when the discriminator is approaching a local optimum, known as the problem of gradient vanishing [183]. This can also lead to mode collapse.…”

Section: Standard Generative Adversarial Network (Gan)mentioning

confidence: 99%

See 1 more Smart Citation

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Sabuhi¹,

Zhou²,

Bezemer³

et al. 2021

Preprint

View full text Add to dashboard Cite

Anomaly detection has become an indispensable tool for modern society, applied in a wide range of applications, from detecting fraudulent transactions to malignant brain tumours. Over time, many anomaly detection techniques have been introduced. However, in general, they all suffer from the same problem: a lack of data that represents anomalous behaviour. As anomalous behaviour is usually costly (or dangerous) for a system, it is difficult to gather enough data that represents such behaviour. This, in turn, makes it difficult to develop and evaluate anomaly detection techniques. Recently, generative adversarial networks (GANs) have attracted a great deal of attention in anomaly detection research, due to their unique ability to generate new data. In this paper, we present a systematic literature review of the applications of GANs in anomaly detection, covering 128 papers on the subject. The goal of this review paper is to analyze and summarize: (1) which anomaly detection techniques can benefit from certain types of GANs, and how, (2) in which application domains GAN-assisted anomaly detection techniques have been applied, and (3) which datasets and performance metrics have been used to evaluate these techniques. Our study helps researchers and practitioners to find the most suitable GAN-assisted anomaly detection technique for their application. In addition, we present a research roadmap for future studies in this area.

show abstract

Section: Standard Generative Adversarial Network (Gan)mentioning

confidence: 99%

Section: Standard Generative Adversarial Network (Gan)mentioning

confidence: 99%

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Sabuhi¹,

Zhou²,

Bezemer³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recent works on Generative Adversarial Networks (GAN) have demonstrated their capability in generating different types of data, from images generation [16,29], text generation [82,87], music composition [41], and time-series sensory data generation [7]. The research published by [25] employed hidden Markov models (HMMs) to generate realistic synthetic smart home sensor data.…”

Section: Synthetic Sensor Data Generationmentioning

confidence: 99%

MoSen: Sensor Network Optimization in Multiple-Occupancy Smart Homes

Zhan

Haddadi

2021

2021 IEEE International Conference on Pervasive Computing and Communications Workshops and Other Affiliated Events (PerCom Work

View full text Add to dashboard Cite

Smart home solutions increasingly rely on a variety of sensors for behavioral analytics and activity recognition to provide contextaware applications and personalized care. Optimizing the sensor network is one of the most important approaches to ensure the classification accuracy and system's efficiency. However, the tradeoff between the cost and performance is often a challenge in real deployments, particularly for multiple-occupancy smart homes or care homes.In this paper, using real indoor activity and mobility traces, floor plans, and synthetic multi-occupancy behavior models, we evaluate several multi-occupancy household scenarios with 2-5 residents. We explore and quantify the trade-offs between the cost of sensor deployments and expected labeling accuracy in different scenarios. Our evaluation across different scenarios show that the performance of the desired context-aware task is affected by different localization resolutions, the number of residents, the number of sensors, and varying sensor deployments. To aid in accelerating the adoption of practical sensor-based activity recognition technology, we design MoSen, a framework to simulate the interaction dynamics between sensor-based environments and multiple residents. By evaluating the factors that affect the performance of the desired sensor network, we provide a sensor selection strategy and design metrics for sensor layout in real environments. Using our selection strategy in a 5-person scenario case study, we demonstrate that MoSen can significantly improve overall system performance without increasing the deployment costs.

show abstract

“…[12], [27] apply REINFORCE [24] algorithm for adversarial training. The third approach, including [2], [29], learns a mapping from the raw discrete feature space to a latent real space, as well as the reverse mapping. These mapping functions are, e.g., realized as an auto-encoder.…”

Section: Related Workmentioning

confidence: 99%

“…A few approaches to generate discrete data with GANs have recently been proposed; most promising are approaches involving reinforcement learning [27], more specifically policy gradients [12]. Another proposed solution is to learn a mapping function from the discrete space of words to a latent real space as well as a reverse mapping [29]. [2] applies this idea to handle categorical features in EHR data and develops auto-encoders to function as the mapping.…”

Section: Introductionmentioning

confidence: 99%

Categorical EHR Imputation with Generative Adversarial Nets

Yang

Tresp

et al. 2019

2019 IEEE International Conference on Healthcare Informatics (ICHI)

View full text Add to dashboard Cite

Electronic Health Records often suffer from missing data, which poses a major problem in clinical practice and clinical studies. A novel approach for dealing with missing data are Generative Adversarial Nets (GANs), which have been generating huge research interest in image generation and transformation. Recently, researchers have attempted to apply GANs to missing data generation and imputation for EHR data: a major challenge here is the categorical nature of the data. State-of-the-art solutions to the GAN-based generation of categorical data involve either reinforcement learning, or learning a bidirectional mapping between the categorical and the a real latent feature space, so that the GANs only need to generate real-valued features. However, these methods are designed to generate complete feature vectors instead of imputing only the subsets of missing features. In this paper we propose a simple and yet effective approach that is based on previous work on GANs for data imputation. We first motivate our solution by discussing the reason why adversarial training often fails in case of categorical features. Then we derive a novel way to re-code the categorical features to stabilize the adversarial training. Based on experiments on two real-world EHR data with multiple settings, we show that our imputation approach largely improves the prediction accuracy, compared to more traditional data imputation approaches.

show abstract

Adversarial Feature Matching for Text Generation

Cited by 35 publications

References 14 publications

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

MoSen: Sensor Network Optimization in Multiple-Occupancy Smart Homes

Categorical EHR Imputation with Generative Adversarial Nets

Contact Info

Product

Resources

About