Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

Unsupervised and self-supervised representation learning has become popular in recent years for learning useful features from unlabelled data. Representation learning has been mostly developed in the neural network literature, and other models for representation learning are surprisingly unexplored. In this work, we introduce and analyze several kernel-based representation learning approaches: Firstly, we define two kernel Self-Supervised Learning (SSL) models using contrastive loss functions and secondly, a Kernel Autoencoder (AE) model based on the idea of embedding and reconstructing data. We argue that the classical representer theorems for supervised kernel machines are not always applicable for (self-supervised) representation learning, and present new representer theorems, which show that the representations learned by our kernel models can be expressed in terms of kernel matrices. We further derive generalisation error bounds for representation learning with kernel SSL and AE, and empirically evaluate the performance of these methods in both small data regimes as well as in comparison with neural network based models.

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging-related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations.

Automated design synthesis has the potential to revolutionize the modern engineering design process and improve access to highly optimized and customized products across countless industries. Successfully adapting generative machine learning to design engineering may enable such automated design synthesis and is a research subject of great importance. We present a review and analysis of deep generative machine learning models in engineering design. Deep generative models (DGMs) typically leverage deep networks to learn from an input dataset and synthesize new designs. Recently, DGMs such as feedforward neural networks (NNs), generative adversarial networks (GANs), variational autoencoders (VAEs), and certain deep reinforcement learning (DRL) frameworks have shown promising results in design applications like structural optimization, materials design, and shape synthesis. The prevalence of DGMs in engineering design has skyrocketed since 2016. Anticipating the continued growth, we conduct a review of recent advances to benefit researchers interested in DGMs for design. We structure our review as an exposition of the algorithms, datasets, representation methods, and applications commonly used in the current literature. In particular, we discuss key works that have introduced new techniques and methods in DGMs, successfully applied DGMs to a design-related domain, or directly supported the development of DGMs through datasets or auxiliary methods. We further identify key challenges and limitations currently seen in DGMs across design fields, such as design creativity, handling constraints and objectives, and modeling both form and functional performance simultaneously. In our discussion, we identify possible solution pathways as key areas on which to target the future work.

Local discriminative representation is needed in many medical image analysis tasks such as identifying sub-types of lesion or segmenting detailed components of anatomical structures. However, the commonly applied supervised representation learning methods require a large amount of annotated data, and unsupervised discriminative representation learning distinguishes different images by learning a global feature, both of which are not suitable for localized medical image analysis tasks. In order to avoid the limitations of these two methods, we introduce local discrimination into unsupervised representation learning in this work. The model contains two branches: one is an embedding branch which learns an embedding function to disperse dissimilar pixels over a low-dimensional hypersphere; and the other is a clustering branch which learns a clustering function to classify similar pixels into the same cluster. These two branches are trained simultaneously in a mutually beneficial pattern, and the learnt local discriminative representations are able to well measure the similarity of local image regions. These representations can be transferred to enhance various downstream tasks. Meanwhile, they can also be applied to cluster anatomical structures from unlabeled medical images under the guidance of topological priors from simulation or other structures with similar topological characteristics. The effectiveness and usefulness of the proposed method are demonstrated by enhancing various downstream tasks and clustering anatomical structures in retinal images and chest X-ray images.KeywordsUnsupervised representation learningLocal discriminationTopological priors

Variational autoencoders (VAE) have ushered in an new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representation learning. In this work, we propose a simple yet powerful class of VAEs that simultaneously result in meaningful learned representations. Our solution is to combine traditional VAEs with mutual information maximization, with the goal to enhance amortized inference in VAEs using Information Theoretic techniques. We call this approach InfoMax-VAE, and such an approach can significantly boost the quality of learned high-level representations. We realize this through explicit maximization of information measures associated with the representation. Using extensive experiments on varied datasets and setups, we show that InfoMax-VAE outperforms contemporary popular approaches, including Info- VAE and β-VAE.

In real-world applications, clustering or classification can usually be improved by fusing information from different views. Therefore, unsupervised representation learning on multi-view data becomes a compelling topic in machine learning. In this paper, we propose a novel and flexible unsupervised multi-view representation learning model termed Collaborative Multi-View Information Bottleneck Networks (CMIB-Nets), which comprehensively explores the common latent structure and the view-specific intrinsic information, and discards the superfluous information in the data significantly improving the generalization capability of the model. Specifically, our proposed model relies on the information bottleneck principle to integrate the shared representation among different views and the view-specific representation of each view, prompting the multi-view complete representation and flexibly balancing the complementarity and consistency among multiple views. We conduct extensive experiments (including clustering analysis, robustness experiment, and ablation study) on real-world datasets, which empirically show promising generalization ability and robustness compared to state-of-the-arts.

Adversarial correlated autoencoder for unsupervised multi-view representation learning

<p><strong>Deep generative models have greatly advanced the field of artificial intelligence by learning the distribution of unlabelled datasets. In this thesis, we aim to develop a novel variational autoencoder (VAE)-based deep generative model that learns meaningful representations for effective unsupervised clustering in the latent space of high-dimensional datasets.</strong></p><p>Existing VAE-based deep clustering algorithms assume a mixture distribution either for the variational posterior over the latent variables or for the prior, to approximate the distribution of unlabelled datasets. The proposed mixtures variational autoencoders (MVAE) model assumes a mixture distribution for both the prior and variational posterior over the latent variables within the VAE framework.</p><p>We apply the variational inference to construct the evidence lower bound (ELBO) of the marginal log-likelihood function for our proposed MVAE model and then derive the analytical form for the clustering assignment estimate, also called the posterior probability estimate. This estimate is associated with each component of the VAE framework and enables the optimization of two distinct ELBO functions based on soft and hard assignment approaches. The training procedure for MVAE involves the joint optimization of both clustering assignment probabilities and model parameters. We evaluate the clustering performance on the latent embeddings of a dataset using both the posterior probability estimate and the Gaussian mixture model (GMM) methods.</p><p>We proposed two variants of the expectation-maximization (EM) algorithm to optimize the parameters for the MVAE model. The MVAE (EM) algorithm provides two distinct, numerically stable solutions for the posterior probability estimate: MVAE(EM-V1), where the estimate is associated with only the prior distribution, and MVAE(EM-V2), where the estimate incorporates both the variational posterior and the prior distribution. Among the proposed models, MVAE(EM-V2) requires less computation time for training. Additionally, this model achieves superior clustering performance on most datasets compared to the baseline models.</p><p>We modified the MVAE(EM-V2) algorithm by including a coefficient (β) with the regularizer term. The trained regularized mixtures VAE model with a small regularization coefficient (β < 1) achieves good unsupervised clustering performance on the test datasets. We further propose a variant of the regularized mixtures VAE model in which the regularization coefficient follows an annealing schedule from β > 1 to β < 1. The scheduled regularized model demonstrates superior clustering accuracy across most benchmark datasets compared to state-of-the-art deep clustering algorithms.</p><p>In this thesis, we point out that assuming a mixture distribution for both the prior and variational posterior components over the latent variables within the VAE framework enhances unsupervised clustering in the latent space. Our proposed models outperform state-of-the-art deep clustering algorithms, including VADE and k-DVAE, as well as the standard VAE model, in cluster analysis of latent representations across most benchmark datasets. Additionally, the proposed models demonstrate reasonable reconstruction performance and generate realistic examples from the latent space.</p>

Materials informatics (MI), which uses artificial intelligence and data analysis techniques to improve the efficiency of materials development, is attracting interests from industry. One of its main applications is the rapid development of novel high-performance compounds. Recently, several deep generative models have been utilized to suggest candidate compounds that are expected to satisfy the desired performance. However, it is practically difficult to obtain sufficient amount of experimental data to train such models. Thus, the authors proposed a deep generative model with nested two variational autoencoders (VAEs). The outer VAE learns the structural features of compounds using large-scale public data, while the inner VAE learns the relationship between the latent variables of the outer VAE and the properties from small-scale experimental data. To generate high performance compounds beyond the range of the training data, the authors also proposed a loss function that amplifies the correlation between a component of latent variables of the inner VAE and material properties. The results indicated that this loss function contributes to improve the probability of generating high-performance candidates. Furthermore, as a result of verification test with an actual customer in chemical industry, it was confirmed that the proposed method is effective in reducing the number of experiments to 1/4 compared to a conventional method.KeywordsVariational AutoencoderDeep generative modelAutomatic compounds designMaterials informatics

Deep generative models are increasingly useful in medical image analysis to solve various issues, including class imbalance in classification tasks, motivating the development of multiple methods, where the Variational Autoencoder (VAE) is recognized as one of the most popular image generators. However, the utilization of convolutional layers in VAEs weakens their ability to model global context and long-range dependencies. This paper presents CAT-VAE, a hybrid approach based on VAE and Cross-Attention Transformers (CAT), in which a cross-attention mechanism is employed to promote long-range dependencies and improve the quality of the generated images. On the Ultrasound breast cancer dataset, the CAT-VAE achieved better image quality (FID 8.7659 for Malignant and 7.8761 for Normal) compared to the standard VAE. An experiment was conducted where a CNN classifier model was trained without data augmentation, with augmentation based on VAE, and using synthetic data generated by CAT-VAE. The CNN achieved the highest accuracy (97.00%) when trained with CAT-VAE synthetic images. A classification accuracy of 86.67% was achieved with mixed datasets of real and synthetic images, demonstrating that CAT-VAE improves generalization and resilience. These results highlight CAT-VAE's ability to produce diverse and realistic synthetic datasets.

Localization in reverberant environments remains an open challenge. Recently, supervised learning approaches have demonstrated very promising results in addressing reverberation. However, even with large data volumes, the number of labels available for supervised learning in such environments is usually small. We propose to address this issue with a semi-supervised learning (SSL) approach, based on deep generative modeling. Our chosen deep generative model, the variational autoencoder (VAE), is trained to generate the phase of relative transfer functions (RTFs) between microphones. In parallel, a direction of arrival (DOA) classifier network based on RTF-phase is also trained. The joint generative and discriminative model, deemed VAE-SSL, is trained using labeled and unlabeled RTF-phase sequences. In learning to generate and classify the sequences, the VAE-SSL extracts the physical causes of the RTF-phase (i.e., source location) from distracting signal characteristics such as noise and speech activity. This facilitates effective end-to-end operation of the VAE-SSL, which requires minimal preprocessing of RTF-phase. VAE-SSL is compared with two signal processing-based approaches, steered response power with phase transform (SRP-PHAT) and MUltiple SIgnal Classification (MUSIC), as well as fully supervised CNNs. The approaches are compared using data from two real acoustic environments - one of which was recently obtained at Technical University of Denmark specifically for our study. We find that VAE-SSL can outperform the conventional approaches and the CNN in label-limited scenarios. Further, the trained VAE-SSL system can generate new RTF-phase samples which capture the physics of the acoustic environment. Thus, the generative modeling in VAE-SSL provides a means of interpreting the learned representations. To the best of our knowledge, this paper presents the first approach to modeling the physics of acoustic propagation using deep generative modeling.

We explore methods of producing adversarial examples on deep generative models such as the variational autoencoder (VAE) and the VAE-GAN. Deep learning architectures are known to be vulnerable to adversarial examples, but previous work has focused on the application of adversarial examples to classification tasks. Deep generative models have recently become popular due to their ability to model input data distributions and generate realistic examples from those distributions. We present three classes of attacks on the VAE and VAE-GAN architectures and demonstrate them against networks trained on MNIST, SVHN and CelebA. Our first attack leverages classification-based adversaries by attaching a classifier to the trained encoder of the target generative model, which can then be used to indirectly manipulate the latent representation. Our second attack directly uses the VAE loss function to generate a target reconstruction image from the adversarial example. Our third attack moves beyond relying on classification or the standard loss for the gradient and directly optimizes against differences in source and target latent representations. We also motivate why an attacker might be interested in deploying such techniques against a target generative network.

Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial networks (GANs) and variational auto-encoders (VAEs). Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. In fact, these models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/VAEs, the discriminators/encoders of GANs/VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field.

Recent advances in deep learning and neural networks have led to an increased interest in the application of generative models in statistical and condensed matter physics. In particular, restricted Boltzmann machines (RBMs) and variational autoencoders (VAEs) as specific classes of neural networks have been successfully applied in the context of physical feature extraction and representation learning. Despite these successes, however, there is only limited understanding of their representational properties and limitations. To better understand the representational characteristics of RBMs and VAEs, we study their ability to capture physical features of the Ising model at different temperatures. This approach allows us to quantitatively assess learned representations by comparing sample features with corresponding theoretical predictions. Our results suggest that the considered RBMs and convolutional VAEs are able to capture the temperature dependence of magnetization, energy, and spin-spin correlations. The samples generated by RBMs are more evenly distributed across temperature than those generated by VAEs. We also find that convolutional layers in VAEs are important to model spin correlations whereas RBMs achieve similar or even better performances without convolutional filters.

Synthetic aperture sonar (SAS) provides high-resolution acoustic imaging by processing coherently the backscattered signal recorded over consecutive pings as the bearing platform moves along a predefined path. Coherent processing requires accurate estimation and compensation of the platform's motion for high quality imaging. The motion of the platform carrying the SAS system can be estimated by cross-correlating redundant recordings at successive pings due to the spatiotemporal coherence of statistically homogeneous backscatter. This data-driven approach for estimating the motion of the SAS platform is essential when positioning information from navigational instruments is absent or inadequately accurate. Herein, the problem of platform motion estimation from coherence measurements of diffuse backscatter is formulated in a probabilistic framework. A variational autoencoder is designed to disentangle the ping-to-ping platform displacement from three-dimensional (3D) spatiotemporal coherence measurements. Unsupervised representation learning from unlabeled data offers robust 3D platform motion estimation. Including a small amount of labeled data during training improves further the platform motion estimation accuracy.