Related papers: Deep Extrapolation for Attribute-Enhanced Generati…
Deep generative models have shown great promise when it comes to synthesising novel images. While they can generate images that look convincing on a higher-level, generating fine-grained details is still a challenge. In order to foster…
Human can extrapolate well, generalize daily knowledge into unseen scenarios, raise and answer counterfactual questions. To imitate this ability via generative models, previous works have extensively studied explicitly encoding Structural…
Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…
We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…
Deep learning-based text classification models need abundant labeled data to obtain competitive performance. Unfortunately, annotating large-size corpus is time-consuming and laborious. To tackle this, multiple researches try to use data…
Generative Adversarial Networks (GANs) are powerful models able to synthesize data samples closely resembling the distribution of real data, yet the diversity of those generated samples is limited due to the so-called mode collapse…
As a kind of generative self-supervised learning methods, generative adversarial nets have been widely studied in the field of anomaly detection. However, the representation learning ability of the generator is limited since it pays too…
This paper investigates the theoretical behavior of generative models under finite training populations. Within the stochastic interpolation generative framework, we derive closed-form expressions for the optimal velocity field and score…
Deep generative models, such as generative adversarial networks (GANs), have been employed for $de~novo$ molecular generation in drug discovery. Most prior studies have utilized reinforcement learning (RL) algorithms, particularly Monte…
It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer…
A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search…
Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural…
Medical image classification is one of the most critical problems in the image recognition area. One of the major challenges in this field is the scarcity of labelled training data. Additionally, there is often class imbalance in datasets…
For years security machine learning research has promised to obviate the need for signature based detection by automatically learning to detect indicators of attack. Unfortunately, this vision hasn't come to fruition: in fact, developing…
Referring Expression Generation (REG) is the task of generating contextually appropriate references to entities. A limitation of existing REG systems is that they rely on entity-specific supervised training, which means that they cannot…
Machine learning algorithms have difficulties to generalize over a small set of examples. Humans can perform such a task by exploiting vast amount of background knowledge they possess. One method for enhancing learning algorithms with…
Automatic question generation according to an answer within the given passage is useful for many applications, such as question answering system, dialogue system, etc. Current neural-based methods mostly take two steps which extract several…
Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…
With the development of speech synthesis, recent research has focused on challenging tasks, such as speaker generation and emotion intensity control. Attribute interpolation is a common approach to these tasks. However, most previous…
Combining Generative Adversarial Networks (GANs) with encoders that learn to encode data points has shown promising results in learning data representations in an unsupervised way. We propose a framework that combines an encoder and a…