In this paper, we propose a generative knowledge transfer technique that trains an RNN based language model (student network) using text and output probabilities generated from a previously trained RNN (teacher network). The text generation can be conducted by either the teacher or the student network. We can also improve the performance by taking the ensemble of soft labels obtained from multiple teacher networks. This method can be used for privacy conscious language model adaptation because no user data is directly used for training. Especially, when the soft labels of multiple devices are aggregated via a trusted third party, we can expect very strong privacy protection.
The idea of style transfer has largely only been explored in image-based tasks, which we attribute in part to the specific nature of loss functions used for style transfer. We propose a general formulation of style transfer as an extension of generative adversarial networks, by using a discriminator to regularize a generator with an otherwise separate loss function. We apply our approach to the task of learning to play chess in the style of a specific player, and present empirical evidence for the viability of our approach.
Many studies have attempted to solve the problem of missing data using various approaches. Among them, Generative Adversarial Imputation Nets (GAIN) was first used to impute data with Generative Adversarial Nets (GAN) and good results were obtained. Subsequent studies have attempted to combine various approaches to address some of its limitations. ClueGAIN is first proposed in this study, which introduces transfer learning into GAIN to solve the problem of poor imputation performance in high missing rate data sets. ClueGAIN can also be used to measure the similarity between data sets to explor…
Iterative generative models, such as noise conditional score networks and denoising diffusion probabilistic models, produce high quality samples by gradually denoising an initial noise vector. However, their denoising process has many steps, making them 2-3 orders of magnitude slower than other generative models such as GANs and VAEs. In this paper, we establish a novel connection between knowledge distillation and image generation with a technique that distills a multi-step denoising process into a single step, resulting in a sampling speed similar to other single-step generative models. Our …
RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；Institute of Mathematics for Industry, Kyushu University（九州大学产业数学研究所）
Prior domain knowledge can greatly help to learn generative models. However, it is often too costly to hard-code prior knowledge as a specific model architecture, so we often have to use general-purpose models. In this paper, we propose a method to incorporate prior knowledge of feature relations into the learning of general-purpose generative models. To this end, we formulate a regularizer that makes the marginals of a generative model to follow prescribed relative dependence of features. It can be incorporated into off-the-shelf learning methods of many generative models, including variation…
We investigate nearest neighbor and generative models for transferring pose between persons. We take in a video of one person performing a sequence of actions and attempt to generate a video of another person performing the same actions. Our generative model (pix2pix) outperforms k-NN at both generating corresponding frames and generalizing outside the demonstrated action set. Our most salient contribution is determining a pipeline (pose detection, face detection, k-NN based pairing) that is effective at perform-ing the desired task. We also detail several iterative improvements and failure mo…
Continual learning of a stream of tasks is an active area in deep neural networks. The main challenge investigated has been the phenomenon of catastrophic forgetting or interference of newly acquired knowledge with knowledge from previous tasks. Recent work has investigated forward knowledge transfer to new tasks. Backward transfer for improving knowledge gained during previous tasks has received much less attention. There is in general limited understanding of how knowledge transfer could aid tasks learned continually. We present a theory for knowledge transfer in continual supervised learnin…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i.e., lifelong generative learning. Although there are some endeavors to tackle this problem, they suffer from high time-consumptions or error accumulation. In this work, we develop an efficient and effective lifelong generative model based on variational autoencoder (VAE). Unlike the generative adversarial network, VAE enjoys high efficiency in the training process, providing natural benefits with few resources. We deduce a lifelong generative model by expending the in…
RealAI（瑞莱智慧）；Peng Cheng Laboratory（鹏城实验室）；Pazhou Laboratory（琶洲实验室）；Tsinghua University（清华大学）；Sea AI Lab（Sea人工智能实验室）
Transfer-based adversarial attacks can evaluate model robustness in the black-box setting. Several methods have demonstrated impressive untargeted transferability, however, it is still challenging to efficiently produce targeted transferability. To this end, we develop a simple yet effective framework to craft targeted transfer-based adversarial examples, applying a hierarchical generative network. In particular, we contribute to amortized designs that well adapt to multi-class targeted attacks. Extensive experiments on ImageNet show that our method improves the success rates of targeted black…
The advancement of the Artificial Intelligence (AI) technologies makes it possible to learn stylistic design criteria from existing maps or other visual art and transfer these styles to make new digital maps. In this paper, we propose a novel framework using AI for map style transfer applicable across multiple map scales. Specifically, we identify and transfer the stylistic elements from a target group of visual examples, including Google Maps, OpenStreetMap, and artistic paintings, to unstylized GIS vector data through two generative adversarial network (GAN) models. We then train a binary cl…
Singapore University of Technology and Design（新加坡科技设计大学）
This paper aims to explore a generative approach for knowledge-based design ideation by applying the latest pre-trained language models in artificial intelligence (AI). Specifically, a method of fine-tuning the generative pre-trained transformer using the USPTO patent database is proposed. The AI-generated ideas are not only in concise and understandable language but also able to synthesize the target design with external knowledge sources with controllable knowledge distance. The method is tested in a case study of rolling toy design and the results show good performance in generating ideas o…
Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods. Nevertheless, these methods are inapplicable for small datasets, which are very common in medical problems. To this end, we propose a knowledge transfer method between diseases via the Generative Bayesian Prior network. Our approach is compared to a pre-train approach and random initialization and obtains the best results in terms of Dice Similarity Coefficient metric for the small subsets of the Brain Tumor Segmentation 2018 database (BRATS2018).
Probabilistic generative models provide a flexible and systematic framework for learning the underlying geometry of data. However, model selection in this setting is challenging, particularly when selecting for ill-defined qualities such as disentanglement or interpretability. In this work, we address this gap by introducing a method for ranking generative models based on the training dynamics exhibited during learning. Inspired by recent theoretical characterizations of disentanglement, our method does not require supervision of the underlying latent factors. We evaluate our approach by demon…
Generative Adversarial Networks (GAN) is an adversarial model, and it has been demonstrated to be effective for various generative tasks. However, GAN and its variants also suffer from many training problems, such as mode collapse and gradient vanish. In this paper, we firstly propose a general crossover operator, which can be widely applied to GANs using evolutionary strategies. Then we design an evolutionary GAN framework C-GAN based on it. And we combine the crossover operator with evolutionary generative adversarial networks (EGAN) to implement the evolutionary generative adversarial netwo…
Carnegie Mellon University（卡内基梅隆大学）；Butlr（Butlr公司）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Generative models which use explicit density modeling (e.g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e.g. Gaussian, to the unknown input distribution. This often requires searching over a class of non-linear functions (e.g., representable by a deep neural network). While effective in practice, the associated runtime/memory costs can increase rapidly, usually as a function of the performance desired in an application. We propose a much cheaper (and simpler) strategy to estimate this mapping based on adapting known results in k…
Application of intelligent systems especially in smart homes and health-related topics has been drawing more attention in the last decades. Training Human Activity Recognition (HAR) models -- as a major module -- requires a fair amount of labeled data. Despite training with large datasets, most of the existing models will face a dramatic performance drop when they are tested against unseen data from new users. Moreover, recording enough data for each new user is unviable due to the limitations and challenges of working with human users. Transfer learning techniques aim to transfer the knowledg…
Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery
Edwardson School of Industrial Engineering and the Institute of Cancer Research, Purdue University（埃德沃兹工业工程学院和癌症研究所，普渡大学）；Elmore Family School of Electrical and Computer Engineering, Purdue University（埃尔摩家庭电气与计算机工程学院，普渡大学）
In real-world applications, it is often expensive and time-consuming to obtain labeled examples. In such cases, knowledge transfer from related domains, where labels are abundant, could greatly reduce the need for extensive labeling efforts. In this scenario, transfer learning comes in hand. In this paper, we propose Deep Variational Transfer (DVT), a variational autoencoder that transfers knowledge across domains using a shared latent Gaussian mixture model. Thanks to the combination of a semi-supervised ELBO and parameters sharing across domains, we are able to simultaneously: (i) align all …
Knowledge tracing aims to track students' knowledge status over time to predict students' future performance accurately. Markov chain-based knowledge tracking (MCKT) models can track knowledge concept mastery probability over time. However, as the number of tracked knowledge concepts increases, the time complexity of MCKT predicting student performance increases exponentially (also called explaining away problem. In addition, the existing MCKT models only consider the relationship between students' knowledge status and problems when modeling students' responses but ignore the relationship betw…
National Research Council Canada（加拿大国家研究委员会）；University of Ottawa（渥太华大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Brock University（布鲁克大学）
Deploying generative machine learning techniques to generate novel chemical structures based on molecular fingerprint representation has been well established in molecular design. Typically, sequential learning (SL) schemes such as hidden Markov models (HMM) and, more recently, in the sequential deep learning context, recurrent neural network (RNN) and long short-term memory (LSTM) were used extensively as generative models to discover unprecedented molecules. To this end, emission probability between two states of atoms plays a central role without considering specific chemical or physical pr…
We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems poses a fundamental trade-off: whether to seek policies that are expected to achieve high (yet sub-optimal) performance in the new task immediately or whether to seek information to quickly identify an optimal solution, potentially at the cost of poor initial behavior. In this work, we focus on the second objective when the agent has access to a generative model…
Carnegie Mellon University（卡内基梅隆大学）；University of California San Diego（加州大学圣地亚哥分校）
We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. Our probabilistic approach models non-parallel data from two domains as a partially observed parallel corpus. By hypothesizing a parallel latent sequence that generates each observed sequence, our model learns to transform sequences from one domain to another in a completely unsupervised fashion. In contrast with traditional generative sequence models (e.g. the HMM), our model makes few assumptions about the data it generates: it uses a recurrent language model as…
Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）
This work addresses fair generative models. Dataset biases have been a major cause of unfairness in deep generative models. Previous work had proposed to augment large, biased datasets with small, unbiased reference datasets. Under this setup, a weakly-supervised approach has been proposed, which achieves state-of-the-art quality and fairness in generated samples. In our work, based on this setup, we propose a simple yet effective approach. Specifically, first, we propose fairTL, a transfer learning approach to learn fair generative models. Under fairTL, we pre-train the generative model with …
Warsaw University of Technology（华沙理工大学）；Jagiellonian University（雅盖隆大学）；Tooploox
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space. Deep generative models suffer from catastrophic forgetting in the same way as other neural structures. Recent generative continual learning works approach this problem and try to learn from new data without forgetting previous knowledge. However, those methods usually focus on artificial scenarios where examples share almost no similarity between subsequent portions of data - an assumption not realistic in the real-life applications of continual learning. In thi…
Knowledge transfer among multiple networks using their outputs or intermediate activations have evolved through extensive manual design from a simple teacher-student approach (knowledge distillation) to a bidirectional cohort one (deep mutual learning). The key factors of such knowledge transfer involve the network size, the number of networks, the transfer direction, and the design of the loss function. However, because these factors are enormous when combined and become intricately entangled, the methods of conventional knowledge transfer have explored only limited combinations. In this pape…
BMW Group（宝马集团）；University of Kassel（卡塞尔大学）；Aalto University（阿尔托大学）
After data selection, pre-processing, transformation, and feature extraction, knowledge extraction is not the final step in a data mining process. It is then necessary to understand this knowledge in order to apply it efficiently and effectively. Up to now, there is a lack of appropriate techniques that support this significant step. This is partly due to the fact that the assessment of knowledge is often highly subjective, e.g., regarding aspects such as novelty or usefulness. These aspects depend on the specific knowledge and requirements of the data miner. There are, however, a number of as…
The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited applicability to the diverse DGMs that can lack a Bayesian formulation or even explicit density evaluation. PR also requires constraints to be fully specified a priori, which is impractical or suboptimal for complex knowledge with learnable uncertain parts. In this paper, we esta…
School of Computing（计算学院）；National University of Singapore（新加坡国立大学）
Early detection of Alzheimer's disease (AD) and identification of potential risk/beneficial factors are important for planning and administering timely interventions or preventive measures. In this paper, we learn a disease model for AD that combines genotypic and phenotypic profiles, and cognitive health metrics of patients. We propose a probabilistic generative subspace that describes the correlative, complementary and domain-specific semantics of the dependencies in multi-view, multi-modality medical data. Guided by domain knowledge and using the latent consensus between abstractions of mul…
Detection of diseases through medical imaging is preferred due to its non-invasive nature. Medical imaging supports multiple modalities of data that enable a thorough and quick look inside a human body. However, interpreting imaging data is often time-consuming and requires a great deal of human expertise. Deep learning models can expedite interpretation and alleviate the work of human experts. However, these models are data-intensive and require significant labeled images for training. During novel disease outbreaks such as Covid-19, we often do not have the required labeled imaging data, esp…
Deep learning-based techniques have been introduced into the field of trajectory optimization in recent years. Deep Neural Networks (DNNs) are trained and used as the surrogates of conventional optimization process. They can provide low thrust (LT) transfer cost estimation and enable more complex preliminary mission designs. However, it is a challenge to efficiently obtain the required amount of trajectory data for training. A Generative Adversarial Network (GAN) is adapted to generate the feasible LT trajectory data efficiently. The GAN consists of a generator and a discriminator, both of whi…
Northeastern University（东北大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
Due to the widespread use of positron emission tomography (PET) in clinical practice, the potential risk of PET-associated radiation dose to patients needs to be minimized. However, with the reduction in the radiation dose, the resultant images may suffer from noise and artifacts that compromise diagnostic performance. In this paper, we propose a parameter-transferred Wasserstein generative adversarial network (PT-WGAN) for low-dose PET image denoising. The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural…
Lakehead University（湖首大学）；Western University（韦仕敦大学）；Harbin Institute of Technology（哈尔滨工业大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；Tianjin University（天津大学）；Okanagan College（奥肯那根学院）；The University of British Columbia Okanagan（不列颠哥伦比亚大学奥肯那根分校）
Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-resolution and low-resolution images are unavailable and the low-resolution images are degraded by complicated and unknown kernels. To break these limitations, we propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adversarial Network (UBCDTL-GAN), which consists of an Unsupervised Bi-directional Cycle Domain Tran…
The biggest challenge faced by a Machine Learning Engineer is the lack of data they have, especially for 2-dimensional images. The image is processed to be trained into a Machine Learning model so that it can recognize patterns in the data and provide predictions. This research is intended to create a solution using the Cycle Generative Adversarial Networks (GANs) algorithm in overcoming the problem of lack of data. Then use Style Transfer to be able to generate a new image based on the given style. Based on the results of testing the resulting model has been carried out several improvements, …
University of Toronto（多伦多大学）；University of Alberta（阿尔伯塔大学）
Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers. While pathologists do not struggle with color variations in slides, computational solutions usually suffer from this critical issue. To address the issue of color variations in histopathology images, this study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial networks. By cooperating structural preservation metrics and feedback of an auxiliary diagnosis net in learning, medical-…
End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc interface between two existing models to solve a new task. Specifically, we take inspiration from neural machine translation, and cast the challenging problem of cross-modal domain transfer as unsupervised translation between the latent spaces of pretrained deep generative models. By abstracting away the data representation, we demonstrate that it is possible …
Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important topic. In this work, we present the results of adapting a speech enhancement generative adversarial network by finetuning the generator with small amounts of data. We investigate the minimum requirements to obtain a stable behavior in terms of several objective metrics in two very different languages: Catalan and Korean. We also study the variability of test perf…
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and replay. In this paper, we propose the use of generative memory that can be recalled in batch samples to train a multi-task agent in a pseudo-rehearsal manner. We show results motivating the need for task-agnostic separation of latent space for the generative memory to address issues …
University of Catania（卡塔尼亚大学）；iCTLab Spinoff of University of Catania（卡塔尼亚大学iCTLab衍生公司）；Banca d’Italia（意大利银行）
Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts. Researchers already demonstrated that synthetic images contain patterns that can determine not only if it is a deepfake but also the generative architecture employed to create the image data itself. These traces can be exploited to study problems that have never been addressed in the context of deepfakes. To this aim, in this paper a first approach to investigate the image ballistics on deepfake images subject to style…
the University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain. It is thus important to explore and understand the factors affecting knowledge transferability. In this paper, as the first work, we analyze and demonstrate the connections between knowledge transferability and another important phenomenon--adversarial transferability, \emph{i.e.}, adversarial examples generated against one model can be transferred to attack other models. Our theoretical studies show that …
Zhejiang University（浙江大学）；AZFT Joint Lab for Knowledge Engine（AZFT知识引擎联合实验室）；Alibaba Group（阿里巴巴集团）
Knowledge graph completion aims to address the problem of extending a KG with missing triples. In this paper, we provide an approach GenKGC, which converts knowledge graph completion to sequence-to-sequence generation task with the pre-trained language model. We further introduce relation-guided demonstration and entity-aware hierarchical decoding for better representation learning and fast inference. Experimental results on three datasets show that our approach can obtain better or comparable performance than baselines and achieve faster inference speed compared with previous methods with pre…
Spatiotemporal Satellite Image Downscaling with Transfer Encoders and Autoregressive Generative Models
University of Toronto（多伦多大学）；Harvard T.H. Chan School of Public Health（哈佛大学T.H. Chan公共卫生学院）；Harvard Medical School（哈佛医学院）；VA Healthcare System Boston, U.S. Department of Veterans Affairs（美国退伍军人事务部波士顿医疗系统）
