Search

In recent years, the application of machine learning techniques for identifying epileptic electroencephalogram (EEG) signals has become increasingly prevalent. In this study, we propose a method called Multi-View Learning and Regularized Label Relaxation Linear Regression (MVRLR) for the recognition of epileptic EEG signals. To be specific, first, we generate multi-view data by employing three different feature extraction methods to capture the EEG features from different perspectives. Then, in the linear regression framework, we introduce a nonnegative label relaxation matrix to transform the strict binary label matrix into a relaxed variable matrix, allowing for more flexible label fitting and expanding the boundaries between different classes. Additionally, we utilize manifold learning to construct a class tightness graph, which serves as a regularization term to prevent overfitting. Finally, we employ Shannon entropy to quantify the overall uncertainty within the probability distribution. To validate the effectiveness of the proposed method, we conduct experiments using a multi-view epileptic EEG dataset and compare it with several other classification algorithms. The extensive experimental results demonstrate that the proposed MVRLR method achieves higher classification accuracy. By applying the proposed method, we can more accurately identify epileptic EEG signals, providing robust support for early diagnosis and personalized treatment of epilepsy. [ABSTRACT FROM AUTHOR]

Multi-view subspace approaches have been extensively studied for their ability to project data onto a low-dimensional space, which is in favour of the clustering task. However, most existing models mainly concentrate on reconstructing data from the sample space, neglecting crucial information from the feature space, and failing to learn an optimal representation. For addressing this issue, we present a new joint framework, dubbed low-rank tensor learning with projection distance metric. This model recovers the original data by learning two low-rank factors, which thoroughly exploits the essential data information. Specifically, a low-rank constraint is introduced on a tensor that integrates subspace representations of all view data, enabling it to capture high-order relationships among views while recovering data from the sample space. Meanwhile, a low-rank projection matrix calculated by decomposing the original features is utilized to enhance data structures via exploring relationships among feature dimensions. Additionally, a distance metric learned by the projection matrix is introduced to leverage the local structure embedded in samples, thereby encouraging the learned representation to be more discriminative. Extensive experimental results on six datasets indicate the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

Semi-supervised learning has attracted more and more attention in medical image segmentation as it alleviates reliance on high-cost annotated data. Meanwhile, existing semi-supervised methods that utilize few labeled data alongside a larger amount of unlabeled data are limited to scenarios where the labeled data comprises at least 10% of the total. However, the effectiveness of these methods significantly diminishes when the proportion of labeled data is extremely low, such as 1% or 5%. Concentrating on this vital yet infrequently addressed scenario, a new method called Diverse Views Cross-Pseudo Supervision (DVCPS) is proposed in this paper. Diverse views at both the data-level and feature-level for unlabeled data are constructed by this method. The Feature Dual Views Network (FDVNet) is introduced, comprising a shared encoder and two distinct decoders. FDVNet is designed to extract both consensus and complementary information from inconsistent views. The predictions generated by the student FDVNet and the pseudo-labels generated by the teacher FDVNet, each produced by different decoders for unlabeled data, are utilized for cross-supervision to acquire complementary information. DVCPS was validated on the ACDC dataset and the MSD Prostate dataset. Compared with other current state-of-the-art methods at specific proportions of labeled data, the best performance in semi-supervised segmentation was achieved by DVCPS. With over a doubling of Dice improvement on each dataset with only 1% labeled data, this demonstrates that DVCPS can effectively address the extreme imbalance of labeled data. [ABSTRACT FROM AUTHOR]

Unsupervised Domain Adaptation (UDA) methods struggle to bridge the gap between a labeled source domain and an unlabeled target domain, particularly due to the rigidity of deep feature representations derived from the penultimate layer of backbone feature extractors. These deeper representations, while discriminative, often fail to generalize under distributional shifts due to their specificity. To overcome these limitations, we introduce a novel representation learning framework, Multi-view Prototypical Transport (MPT), which leverages a multi-view hypothesis model to integrate and utilize the general information present in shallower layers. This approach facilitates a more comprehensive understanding of the relationships among intermediate features. Additionally, our framework incorporates a novel multi-view prototypical learning strategy that not only transfers domain-general representations, but also significantly enhances robustness against target domain outliers. Extensive experimental evaluations on various benchmark datasets demonstrate that our method outperforms existing state-of-the-art UDA approaches, confirming the effectiveness of our strategy in adapting to complex domain shifts.

Recent studies highlight the growing appeal of multi-view learning due to its enhanced generalization. Semi-supervised classification, using few labeled samples to classify the unlabeled majority, is gaining popularity for its time and cost efficiency, particularly with high-dimensional and large-scale multi-view data. Existing graph-based methods for multi-view semi-supervised classification still have potential for improvement in further enhancing classification accuracy. Since deep random walk has demonstrated promising performance across diverse fields and shows potential for semi-supervised classification. This paper proposes a deep random walk inspired multi-view graph convolutional network model for semi-supervised classification tasks that builds signal propagation between connected vertices of the graph based on transfer probabilities. The learned representation matrices from different views are fused by an aggregator to learn appropriate weights, which are then normalized for label prediction. The proposed method partially reduces overfitting, and comprehensive experiments show it delivers impressive performance compared to other state-of-the-art algorithms, with classification accuracy improving by more than 5% on certain test datasets. [ABSTRACT FROM AUTHOR]

Software defect prediction plays a crucial role as a quality assurance technology in software development. The software metrics are associated with the software quality and are vital for prediction models. Most existing defect prediction methods build the prediction model ignoring the complementary information between these two kinds of metrics. In this work, we intend to jointly leverage these two kinds of metrics. For a software instance, we regard the product metrics and the process metrics as its two views. We model the problem of discriminative feature learning from these two kinds of metrics as the problem of multi-view learning. However, it is a challenging task to construct an effective prediction model based on both product and process metrics due to the heterogeneity in data of product and process metrics, and the defect data often has class imbalance characteristic. How to explore the discriminant both inter-view and intra-view effectively has not been well studied. These characteristics make it challenging to construct an effective prediction model. In this paper, we propose a Deep Multi-view Defect Prediction (DMDP) approach, which can predict software defect based on both product and process metrics. We design a neural network with two sub-network branches, which are enforced to share the weights in the last output layer, to map the data from different views to a common space. To guide the training of networks, we design the loss function including the discrepancy loss, discrimination loss and classification loss, which further promotes the distribution consistency across views, makes full use of label information to obtain the discriminative representations, and utilizes the complementarity information for prediction. To alleviate the class imbalance problem, we design a dynamic sampling strategy for dealing with class-imbalanced data. Comprehensive experiments are conducted on 15 projects from three widely used defect datasets. The experimental results demonstrate that multi-view learning based on product and process metrics is helpful for software defect prediction and DMDP outperforms the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Abstract Background and objective Positron emission tomography/computed tomography (PET/CT) is recommended as the standard imaging modality for diffuse large B-cell lymphoma (DLBCL) staging. However, many studies have neglected the role of patients' prognostic factors with respect to imaging PET/CT of quantitative features. In this paper, a multi-view learning (MVL) model is established to make full use of both clinical and imaging data to predict the prognosis of DLBCL patients and thereby assist doctors in decision-making. Methods Feature engineering, including feature extraction, feature screening by recursive feature elimination, and dimensionality reduction by principal component analysis, are successively performed on the clinical data and imaging data of the research subjects to obtain the study data. After dividing the data into training and test sets, an instance weighting method is applied to the training data. Subsequently, kernel mapping is performed on the imaging features and clinical features separately, and this kernel mapping is processed in the new kernel feature space using kernel canonical correlation analysis (KCCA). Lastly, model training is performed on the obtained common kernel subspace using a support vector machine (SVM). The final overall model, named SVM-2view-KCCA (SVM-2 K), was compared with three other multi-view models (Ensemble-SVM, Multi-view maximum entropy discrimination, and canonical correlation analysis). The performance of the model was evaluated on the test data with respect to several dichotomous metrics: accuracy, sensitivity, F1 score, the area under the curve (AUC), and G-mean. Results The SVM model improved AUC by 10.5%, sensitivity by 11.9%, accuracy by 9.8%, F1 score by 9.2%, and G-mean by 7.8% for the DLBCL test data after feature engineering based on dimensionality reduction and instance weighting. In the performance comparison of single-view learning models, the SVM-based integration of clinical and imaging features achieved the best overall performance (AUC = 86.3%, accuracy = 91.6%, sensitivity = 83.2%, F1 = 85.7%, and G-mean = 86.1%). In the comparison of MVL models, SVM-2 K achieved the best overall performance (AUC = 92.1%, accuracy = 96.9%, sensitivity = 90.9%, F1 = 92.8%, and G-mean = 91.4%), and the performance of each MVL model was better than that of the best single-view learning model. Conclusions MVL models outperformed single-view learning models. Of the MVL models, the proposed SVM-2 K achieved the best overall performance and could accurately predict patient prognosis.

Multi-atlas based segmentation techniques constitute an effective approach in the automatic segmentation of medical images. Existing methods usually rely on single spectral descriptors extracted from a specific imaging modality. In this paper, we propose the Multi-View Knee Cartilage Segmentation (MV-KCS) approach, for segmenting the knee joint articular cartilage from MR images. Operating under the Semi-supervised learning framework, MV-KCS leverages spectral content from multiple feature spaces by constructing sparse graphs for each view individually, and aggregating them via optimisation to obtain a common data graph. In We consider two multi-view scenarios: in the former case views correspond to multiple feature descriptors, while on the latter, the views correspond to multiple image modalities. We propose two effective labelling schemes, implementing label propagation from the atlas library to the target image. The proposed methodology is applied to the publicly available Osteoarthritis Initiative repository. We devise a comprehensive experimental design to validate different test cases, comparing single-feature vs multi-features, multi-features vs feature stacking and multi-features vs multi-modalities. Comparative results and statistical analysis reveal that the proposed MV-KCS provides enhanced performance ($DSC = 92.56\% \left({FC} \right), 89.91\% \left({TC} \right)$ DSC = 92.56 % FC , 89.91 % TC ), outperforming a series of patch-based approaches, six recent state-of-the-art deep supervised models and three deep semi-supervised ones, in terms of both classification and volumetric measures. [ABSTRACT FROM AUTHOR]

Since multi-view learning leverages complementary information from multiple feature sets to improve model performance, a tensor-based data fusion layer for neural networks, called Multi-View Data Tensor Fusion (MV-DTF), is used. It fuses M feature spaces X 1 , ⋯ , X M , referred to as views, in a new latent tensor space, S , of order P and dimension J 1 × ⋯ × J P , defined in the space of affine mappings composed of a multilinear map T : X 1 × ⋯ × X M → S —represented as the Einstein product between a (P + M) -order tensor A anda rank-one tensor, X = x (1) ⊗ ⋯ ⊗ x (M) , where x (m) ∈ X m is the m-th view—and a translation. Unfortunately, as the number of views increases, the number of parameters that determine the MV-DTF layer grows exponentially, and consequently, so does its computational complexity. To address this issue, we enforce low-rank constraints on certain subtensors of tensor A using canonical polyadic decomposition, from which M other tensors U (1) , ⋯ , U (M) , called here Hadamard factor tensors, are obtained. We found that the Einstein product A ⊛ M X can be approximated using a sum of R Hadamard products of M Einstein products encoded as U (m) ⊛ 1 x (m) , where R is related to the decomposition rank of subtensors of A. For this relationship, the lower the rank values, the more computationally efficient the approximation. To the best of our knowledge, this relationship has not previously been reported in the literature. As a case study, we present a multitask model of vehicle traffic surveillance for occlusion detection and vehicle-size classification tasks, with a low-rank MV-DTF layer, achieving up to 92.81 % and 95.10 % in the normalized weighted Matthews correlation coefficient metric in individual tasks, representing a significant 6 % and 7 % improvement compared to the single-task single-view models. [ABSTRACT FROM AUTHOR]

Multi-view anomaly detection aims to identify anomalous instances whose patterns are disparate across different views, and existing works usually project the multi-view data into a common subspace for abnormal instance identification. Nevertheless, these methods often fail to explicitly excavate the inter-view dependency and discrepancy among the multi-view data, which are of crucial importance to detect inconsistent patterns across different views interactively. To address this problem, we propose an efficient multi-view anomaly detection method via instance-neighborhood aligning and cross-view reasoning, which can well parse the inter-view dependency and discrepancy to detect various kinds of anomalous multi-view instances. To be specific, we first utilize the view-specific encoder to project the original data into the latent feature space, in which a novel instance-neighborhood aligning scheme is seamlessly embedded to preserve the consistent neighborhood structures of multiple views and maximize the consistency for the semantically relevant instances, which indirectly enhances the inter-view dependencies. Meanwhile, a cross-view reasoning module is efficiently designed to explore the inter-view dependencies and discrepancies, which can explicitly boost the inter-view correlations and differences to reason the inconsistent view patterns. Through the joint exploitation of the view-specific reconstruction loss, instance-neighborhood aligning loss, and cross-view reasoning loss, different kinds of anomalous multi-view instances can be well detected more reliably. Extensive experiments evaluated on benchmark datasets, quantitatively and qualitatively, verify the advantages of the proposed multi-view anomaly detection framework and show its substantial improvements over the state of the arts. The code is available at: . [ABSTRACT FROM AUTHOR]

Geophysical data are often integrated into geological data for 3D modeling of underground spaces. However, the existing single-view approach means it is difficult to adequately fuse the valid information between the two types of data, and the complexity of lithological decoding and classification is high. To address this issue, a multi-view ensemble machine learning (ML) framework is proposed. Initially, the original dataset of lithology prediction is constructed by aligning geological and geophysical data with different spatial scales. Next, the dataset is divided into three datasets of structural strength, density, and moisture content according to the lithology properties of the geophysical data. The proposed framework is then used to capture the lithologic characteristics under different views to achieve the prediction of lithologic labels. In this process, a self-attentive mechanism is used to adaptively fuse the valid information under each view. To validate the proposed framework, it is applied to a project in Jiaxing, Zhejiang Province, China. Compared with existing ML methods, the proposed multi-view ensemble ML framework improves modeling accuracy and constructs models with low uncertainty. The framework can be extended to other multi-source data fusion tasks across geoscience domains. [ABSTRACT FROM AUTHOR]

Background and objective: Positron emission tomography/computed tomography (PET/CT) is recommended as the standard imaging modality for diffuse large B-cell lymphoma (DLBCL) staging. However, many studies have neglected the role of patients' prognostic factors with respect to imaging PET/CT of quantitative features. In this paper, a multi-view learning (MVL) model is established to make full use of both clinical and imaging data to predict the prognosis of DLBCL patients and thereby assist doctors in decision-making. Methods: Feature engineering, including feature extraction, feature screening by recursive feature elimination, and dimensionality reduction by principal component analysis, are successively performed on the clinical data and imaging data of the research subjects to obtain the study data. After dividing the data into training and test sets, an instance weighting method is applied to the training data. Subsequently, kernel mapping is performed on the imaging features and clinical features separately, and this kernel mapping is processed in the new kernel feature space using kernel canonical correlation analysis (KCCA). Lastly, model training is performed on the obtained common kernel subspace using a support vector machine (SVM). The final overall model, named SVM-2view-KCCA (SVM-2 K), was compared with three other multi-view models (Ensemble-SVM, Multi-view maximum entropy discrimination, and canonical correlation analysis). The performance of the model was evaluated on the test data with respect to several dichotomous metrics: accuracy, sensitivity, F1 score, the area under the curve (AUC), and G-mean. Results: The SVM model improved AUC by 10.5%, sensitivity by 11.9%, accuracy by 9.8%, F1 score by 9.2%, and G-mean by 7.8% for the DLBCL test data after feature engineering based on dimensionality reduction and instance weighting. In the performance comparison of single-view learning models, the SVM-based integration of clinical and imaging features achieved the best overall performance (AUC = 86.3%, accuracy = 91.6%, sensitivity = 83.2%, F1 = 85.7%, and G-mean = 86.1%). In the comparison of MVL models, SVM-2 K achieved the best overall performance (AUC = 92.1%, accuracy = 96.9%, sensitivity = 90.9%, F1 = 92.8%, and G-mean = 91.4%), and the performance of each MVL model was better than that of the best single-view learning model. Conclusions: MVL models outperformed single-view learning models. Of the MVL models, the proposed SVM-2 K achieved the best overall performance and could accurately predict patient prognosis. [ABSTRACT FROM AUTHOR]

With the explosive growth of user-generated content, multi-view learning has become a rapidly growing direction in pattern recognition and data analysis areas. Due to the significant application value of multi-view learning, there has been a continuous emergence of research based on machine learning methods and traditional deep learning paradigms. The core challenge in multi-view learning lies in harnessing both consistent and complementary information to forge a unified, comprehensive representation. However, many multi-view learning tasks are based on graph-structured data, making existing methods unable to effectively mine the information contained in the input multiple data sources. Recently, graph neural networks (GNN) techniques have been widely utilized to deal with non-Euclidean data, such as graphs or manifolds. Thus, it is essential to combine the advantages of the powerful learning capability of GNN models and multi-view data. In this paper, we aim to provide a comprehensive survey of recent research works on GNN-based multi-view learning. In detail, we first provide a taxonomy of GNN-based multi-view learning methods according to the input form of models: multi-relation, multi-attribute and mixed. Then, we introduce the applications of multi-view learning, including recommendation systems, computer vision and so on. Moreover, several public datasets and open-source codes are introduced for implementation. Finally, we analyze the challenges of applying GNN models on various multi-view learning tasks and state new future directions in this field. [ABSTRACT FROM AUTHOR]

Feature extraction research has witnessed significant advancements in recent decades, particularly with single-view graph embedding (GE) methods that demonstrate clear advantages by incorporating structural information. However, multi-view data includes descriptions from various perspectives or sensors, offering richer and more comprehensive information compared to single-view data. Research interest in multi-view feature extraction is steadily increasing. Hence, there is a pressing need for a comprehensive framework that extends single-view methods, especially effective GE methods, into multi-view approaches. This article proposes three innovative multi-view feature extraction frameworks based on regression embedding. These frameworks extend single-view GE methods to the multi-view scenario. Our approach meticulously considers the consistency and complementarity of multi-view data, placing strong emphasis on robustness to noisy datasets. Additionally, the use of non-linear shared embedding helps prevent the loss of essential information that may occur with linear projection techniques. Through numerical experiments, we validate the effectiveness and robustness of our proposed frameworks on both real and noisy datasets. [ABSTRACT FROM AUTHOR]

Classification of epileptic electroencephalograms can provide strong technical support for early warning and monitoring of epilepsy. However, Electroencephalogram (EEG) has characteristics of specificity, multi-feature, and susceptibility to noise interference. Therefore, this paper proposes a joint low-rank representation and transfer multi-view learning (LRR-TML) approach for EEG epilepsy classification. The LRR-TML approach inherits the advantages of low-rank representation, filters redundant features and noise information, and focuses on the main feature and significant feature of EEG. The LRR-TML approach introduces the ideas of transfer learning and multi-view learning on the framework of low-rank representation, mines the linear correlation between different domains in the subspace through low-rank representation, and effectively transfers the discriminative knowledge of the source domain to the target domain. According to the principles of complementarity and consistency of views, the LRR-TML approach comprehensively describes EEG by integrating various features, maximizing the consistency between different views and minimizing the divergence between views. Experimental results on the Bonn dataset show that the LRR-TML approach achieves the best classification results among all comparison approaches. [ABSTRACT FROM AUTHOR]

Epidemiologic and genetic studies in many complex diseases suggest subgroup disparities (e.g. by sex, race) in disease course and patient outcomes. We consider this from the standpoint of integrative analysis where we combine information from different views (e.g. genomics, proteomics, clinical data). Existing integrative analysis methods ignore the heterogeneity in subgroups, and stacking the views and accounting for subgroup heterogeneity does not model the association among the views. We propose Heterogeneity in Integration and Prediction (HIP), a statistical approach for joint association and prediction that leverages the strengths in each view to identify molecular signatures that are shared by and specific to a subgroup. We apply HIP to proteomics and gene expression data pertaining to chronic obstructive pulmonary disease (COPD) to identify proteins and genes shared by, and unique to, males and females, contributing to the variation in COPD, measured by airway wall thickness. Our COPD findings have identified proteins, genes, and pathways that are common across and specific to males and females, some implicated in COPD, while others could lead to new insights into sex differences in COPD mechanisms. HIP accounts for subgroup heterogeneity in multi-view data, ranks variables based on importance, is applicable to univariate or multivariate continuous outcomes, and incorporates covariate adjustment. With the efficient algorithms implemented using PyTorch, this method has many potential scientific applications and could enhance multiomics research in health disparities. HIP is available at https://github.com/lasandrall/HIP , a video tutorial at https://youtu.be/O6E2OLmeMDo and a Shiny Application at https://multi-viewlearn.shinyapps.io/HIP%5fShinyApp/ for users with limited programming experience. [ABSTRACT FROM AUTHOR]

Abstract The identification and classification of various phenotypic features of Auricularia cornea fruit bodies are crucial for quality grading and breeding efforts. The phenotypic features of Auricularia cornea fruit bodies encompass size, number, shape, color, pigmentation, and damage. These phenotypic features are distributed across various views of the fruit bodies, making the task of achieving both rapid and accurate identification and classification challenging. This paper proposes a novel multi-view multi-label fast network that integrates two different views of the Auricularia cornea fruiting body, enabling rapid and precise identification and classification of six phenotypic features simultaneously. Initially, a multi-view feature extraction model based on partial convolution was constructed. This model incorporates channel attention mechanisms to achieve rapid phenotypic feature extraction of the Auricularia cornea fruiting body. Subsequently, an efficient multi-task classifier was designed, based on class-specific residual attention, to ensure accurate classification of phenotypic features. Finally, task weights were dynamically adjusted based on heteroscedastic uncertainty, reducing the training complexity of the multi-task classification. The proposed network achieved a classification accuracy of 94.66% and an inference speed of 11.9 ms on an image dataset of dried Auricularia cornea fruiting bodies with three views and six labels. The results demonstrate that the proposed network can efficiently and accurately identify and classify all phenotypic features of Auricularia cornea.

The identification and classification of various phenotypic features of Auricularia cornea fruit bodies are crucial for quality grading and breeding efforts. The phenotypic features of Auricularia cornea fruit bodies encompass size, number, shape, color, pigmentation, and damage. These phenotypic features are distributed across various views of the fruit bodies, making the task of achieving both rapid and accurate identification and classification challenging. This paper proposes a novel multi-view multi-label fast network that integrates two different views of the Auricularia cornea fruiting body, enabling rapid and precise identification and classification of six phenotypic features simultaneously. Initially, a multi-view feature extraction model based on partial convolution was constructed. This model incorporates channel attention mechanisms to achieve rapid phenotypic feature extraction of the Auricularia cornea fruiting body. Subsequently, an efficient multi-task classifier was designed, based on class-specific residual attention, to ensure accurate classification of phenotypic features. Finally, task weights were dynamically adjusted based on heteroscedastic uncertainty, reducing the training complexity of the multi-task classification. The proposed network achieved a classification accuracy of 94.66% and an inference speed of 11.9 ms on an image dataset of dried Auricularia cornea fruiting bodies with three views and six labels. The results demonstrate that the proposed network can efficiently and accurately identify and classify all phenotypic features of Auricularia cornea. [ABSTRACT FROM AUTHOR]

Due to the heterogeneity gap in multi-view data, researchers have been attempting to apply these data to learn a co-latent representation to bridge this gap. However, multi-view representation learning still confronts two challenges: (1) it is hard to simultaneously consider the performance of downstream tasks and the interpretability and transparency of the network; (2) it fails to learn representations that accurately describe the class boundaries of downstream tasks. To overcome these limitations, we propose an interpretable representation learning framework, named interpretable multi-view proximity representation learning network. On the one hand, the proposed network is customized by an explicitly designed optimization objective that enables it to learn semantic co-latent representations while maintaining the interpretability and transparency of the network from the design level. On the other hand, the designed multi-view proximity representation learning objective function encourages its learned co-latent representations to form intuitive class boundaries by increasing the inter-class distance and decreasing the intra-class distance. Driven by a flexible downstream task loss, the learned co-latent representation can adapt to various multi-view scenarios and has been shown to be effective in experiments. As a result, this work provides a feasible solution to a generalized multi-view representation learning framework and is expected to accelerate the research and exploration in this field. [ABSTRACT FROM AUTHOR]

Mendelian randomization (MR) provides valuable assessments of the causal effect of exposure on outcome, yet the application of conventional MR methods for mapping risk genes encounters new challenges. One of the issues is the limited availability of expression quantitative trait loci (eQTLs) as instrumental variables (IVs), hampering the estimation of sparse causal effects. Additionally, the often context- or tissue-specific eQTL effects challenge the MR assumption of consistent IV effects across eQTL and GWAS data. To address these challenges, we propose a multi-context multivariable integrative MR framework, mintMR, for mapping expression and molecular traits as joint exposures. It models the effects of molecular exposures across multiple tissues in each gene region, while simultaneously estimating across multiple gene regions. It uses eQTLs with consistent effects across more than one tissue type as IVs, improving IV consistency. A major innovation of mintMR involves employing multi-view learning methods to collectively model latent indicators of disease relevance across multiple tissues, molecular traits, and gene regions. The multi-view learning captures the major patterns of disease relevance and uses these patterns to update the estimated tissue relevance probabilities. The proposed mintMR iterates between performing a multi-tissue MR for each gene region and joint learning the disease-relevant tissue probabilities across gene regions, improving the estimation of sparse effects across genes. We apply mintMR to evaluate the causal effects of gene expression and DNA methylation for 35 complex traits using multi-tissue QTLs as IVs. The proposed mintMR controls genome-wide inflation and offers insights into disease mechanisms. Mendelian randomization (MR) faces challenges in mapping risk genes due to limited and tissue-specific instrumental variables. We propose mintMR, a multi-context multivariable integrative MR framework, that models molecular exposure effects across multiple tissues for each gene region and estimates multiple gene regions simultaneously, improving causal gene identification. [ABSTRACT FROM AUTHOR]

Unsupervised representation learning for 3D shapes has become a critical problem for large-scale 3D shape management. Recent model-based methods for this task require additional information for training, while popular view-based methods often overlook viewpoint variance in view prediction, leading to uninformative 3D features that limit their practical applications. To address these issues, we propose an unsupervised 3D shape representation learning method called View Sequence Prediction GAN (VSP-GAN), which decomposes view content and viewpoint variance. VSP-GAN takes several adjacent views of a 3D shape as input and outputs the subsequent views. The key idea is to split the multi-view sequence into two available perceptible parts, view content and viewpoint variance, and independently encode them with separate encoders. With the information, we design a decoder implemented by the mirrored architecture of the content encoder to predict the view sequence by multi-steps. Besides, to improve the quality of the reconstructed views, we propose a novel hierarchical view prediction loss to enhance view realism, semantic consistency, and details retainment. We evaluate the proposed VSP-GAN on two popular 3D CAD datasets, ModelNet10 and ModelNet40, for 3D shape classification and retrieval. The experimental results demonstrate that our VSP-GAN can learn more discriminative features than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]