View-specific Representations Research Articles

SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering

Deep Multi-view Graph Clustering (DMGC) aims to partition instances into different groups using the graph information extracted from multi-view data. The mainstream framework of DMGC methods applies graph neural networks to embed structure information into the view-specific representations and fuse them for the consensus representation. However, on one hand, we find that the graph learned in advance is not ideal for clustering as it is constructed by original multi-view data and localized connecting. On the other hand, most existing methods learn the consensus representation in a late fusion manner, which fails to propagate the structure relations across multiple views. Inspired by the observations, we propose a Structure-adaptive Unified gRaph nEural network for multi-view clusteRing (SURER), which can jointly learn a heterogeneous multi-view unified graph and robust graph neural networks for multi-view clustering. Specifically, we first design a graph structure learning module to refine the original view-specific attribute graphs, which removes false edges and discovers the potential connection. According to the view-specific refined attribute graphs, we integrate them into a unified heterogeneous graph by linking the representations of the same sample from different views. Furthermore, we use the unified heterogeneous graph as the input of the graph neural network to learn the consensus representation for each instance, effectively integrating complementary information from various views. Extensive experiments on diverse datasets demonstrate the superior effectiveness of our method compared to other state-of-the-art approaches.

Deep Incomplete Multi-View Learning Network with Insufficient Label Information

Due to the efficiency of integrating semantic consensus and complementary information across different views, multi-view classification methods have attracted much attention in recent years. However, multi-view data often suffers from both the miss of view features and insufficient label information, which significantly decrease the performance of traditional multi-view classification methods in practice. Learning for such simultaneous lack of feature and label is crucial but rarely studied. To tackle these problems, we propose a novel Deep Incomplete Multi-view Learning Network (DIMvLN) by incorporating graph networks and semi-supervised learning in this paper. Specifically, DIMvLN firstly designs the deep graph networks to effectively recover missing data with assigning pseudo-labels of large amounts of unlabeled instances and refine the incomplete feature information. Meanwhile, to enhance the label information, a novel pseudo-label generation strategy with the similarity constraints of unlabeled instances is proposed to exploit additional supervisory information and guide the completion module to preserve more semantic information of absent multi-view data. Besides, we design view-specific representation extractors with the autoencoder structure and contrastive loss to learn high-level semantic representations for each view, promote cross-view consistencies and augment the separability between different categories. Finally, extensive experimental results demonstrate the effectiveness of our DIMvLN, attaining noteworthy performance improvements compared to state-of-the-art competitors on several public benchmark datasets. Code will be available at GitHub.

AMCFCN: attentive multi-view contrastive fusion clustering net

Advances in deep learning have propelled the evolution of multi-view clustering techniques, which strive to obtain a view-common representation from multi-view datasets. However, the contemporary multi-view clustering community confronts two prominent challenges. One is that view-specific representations lack guarantees to reduce noise introduction, and another is that the fusion process compromises view-specific representations, resulting in the inability to capture efficient information from multi-view data. This may negatively affect the accuracy of the clustering results. In this article, we introduce a novel technique named the “contrastive attentive strategy” to address the above problems. Our approach effectively extracts robust view-specific representations from multi-view data with reduced noise while preserving view completeness. This results in the extraction of consistent representations from multi-view data while preserving the features of view-specific representations. We integrate view-specific encoders, a hybrid attentive module, a fusion module, and deep clustering into a unified framework called AMCFCN. Experimental results on four multi-view datasets demonstrate that our method, AMCFCN, outperforms seven competitive multi-view clustering methods. Our source code is available at https://github.com/xiaohuarun/AMCFCN.

Trustworthy multi-view clustering via alternating generative adversarial representation learning and fusion

Multi-view clustering (MVC) has attached extensive attention as it provides an effective approach to deal with the unlabeled data in real-world applications. To enjoy the strong feature extraction capacity of deep learning, traditional shallow MVC methods are further extended to deep version. Though achieve superiorities in many fields, most existing deep MVC models are still limited by their lacking assurance of the trustworthiness and robustness. This drawback also leads to the possible poor clustering performance. To tackle this drawback, we propose an alternating generative adversarial learning strategy based network, termed as Alternating Generative Adversarial Representation Learning (AGARL) network for multi-view clustering, aiming to drive different views to fall into the same semantic space for the further alignment and information fusion. Various from the traditional generative adversarial learning strategy, the proposed alternating adversarial representation learning strategy successes in further aligning the distributions of the view-specific representations and exploring the cross-view consistency credited by its setting each view as the reference alternately. Then a consensus representative latent representation can be learned through an attention-like sub-network for all views. Finally, a self-supervised clustering module is employed in the proposed network to guide the learning of cluster assignment. In addition, comprehensive experiments on numerous benchmark MVC datasets have been performed to demonstrate the effectiveness of the proposed network compared to other state-of-the-art methods.

Clustering Enhanced Multiplex Graph Contrastive Representation Learning.

Multiplex graph representation learning has attracted considerable attention due to its powerful capacity to depict multiple relation types between nodes. Previous methods generally learn representations of each relation-based subgraph and then aggregate them into final representations. Despite the enormous success, they commonly encounter two challenges: 1) the latent community structure is overlooked and 2) consistent and complementary information across relation types remains largely unexplored. To address these issues, we propose a clustering-enhanced multiplex graph contrastive representation learning model (CEMR). In CEMR, by formulating each relation type as a view, we propose a multiview graph clustering framework to discover the potential community structure, which promotes representations to incorporate global semantic correlations. Moreover, under the proposed multiview clustering framework, we develop cross-view contrastive learning and cross-view cosupervision modules to explore consistent and complementary information in different views, respectively. Specifically, the cross-view contrastive learning module equipped with a novel negative pairs selecting mechanism enables the view-specific representations to extract common knowledge across views. The cross-view cosupervision module exploits the high-confidence complementary information in one view to guide low-confidence clustering in other views by contrastive learning. Comprehensive experiments on four datasets confirm the superiority of our CEMR when compared to the state-of-the-art rivals.

Semisupervised Progressive Representation Learning for Deep Multiview Clustering.

Multiview clustering has become a research hotspot in recent years due to its excellent capability of heterogeneous data fusion. Although a great deal of related works has appeared one after another, most of them generally overlook the potentials of prior knowledge utilization and progressive sample learning, resulting in unsatisfactory clustering performance in real-world applications. To deal with the aforementioned drawbacks, in this article, we propose a semisupervised progressive representation learning approach for deep multiview clustering (namely, SPDMC). Specifically, to make full use of the discriminative information contained in prior knowledge, we design a flexible and unified regularization, which models the sample pairwise relationship by enforcing the learned view-specific representation of must-link (ML) samples (cannot-link (CL) samples) to be similar (dissimilar) with cosine similarity. Moreover, we introduce the self-paced learning (SPL) paradigm and take good care of two characteristics in terms of both complexity and diversity when progressively learning multiview representations, such that the complementarity across multiple views can be squeezed thoroughly. Through comprehensive experiments on eight widely used image datasets, we prove that the proposed approach can perform better than the state-of-the-art opponents.

Hierarchical graph augmented stacked autoencoders for multi-view representation learning

With recent success of deep neural networks, stacked autoencoder networks have received a lot of attention for robust unsupervised representation learning. However, recent autoencoder methods cannot make full use of multi-view information and thus fail to further improve many real-world applications by exploring the geometric structures of multi-view data. To address the above-mentioned issue, we introduce hierarchical graph augmented stacked autoencoders (HGSAE) for unsupervised multi-view representation learning. Specifically, a hierarchical graph structure is first adapted to stacked autoencoders to learn view-specific representations, aiming to preserve the geometric information of multi-view data through local and non-local graph regularizations. A general or common representation can then be learned by reconstructing each single view using fully connected neural networks. By doing this, the proposed method not only preserves the geometric information in multi-view data but also automatically balances the complementarity/consistency among different views. Extensive experiments on six popular unsupervised representation learning datasets demonstrate the effectiveness of our method when compared with recent state-of-the-art autoencoder methods.

Progressive Deep Multi-View Comprehensive Representation Learning

Multi-view Comprehensive Representation Learning (MCRL) aims to synthesize information from multiple views to learn comprehensive representations of data items. Prevalent deep MCRL methods typically concatenate synergistic view-specific representations or average aligned view-specific representations in the fusion stage. However, the performance of synergistic fusion methods inevitably degenerate or even fail when partial views are missing in real-world applications; the aligned based fusion methods usually cannot fully exploit the complementarity of multi-view data. To eliminate all these drawbacks, in this work we present a Progressive Deep Multi-view Fusion (PDMF) method. Considering the multi-view comprehensive representation should contain complete information and the view-specific data contain partial information, we deem that it is unstable to directly learn the mapping from partial information to complete information. Hence, PDMF employs a progressive learning strategy, which contains the pre-training and fine-tuning stages. In the pre-training stage, PDMF decodes the auxiliary comprehensive representation to the view-specific data. It also captures the consistency and complementarity by learning the relations between the dimensions of the auxiliary comprehensive representation and all views. In the fine-tuning stage, PDMF learns the mapping from the original data to the comprehensive representation with the help of the auxiliary comprehensive representation and relations. Experiments conducted on a synthetic toy dataset and 4 real-world datasets show that PDMF outperforms state-of-the-art baseline methods. The code is released at https://github.com/winterant/PDMF.

DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification

In recent years, multi-view multi-label learning has aroused extensive research enthusiasm. However, multi-view multi-label data in the real world is commonly incomplete due to the uncertain factors of data collection and manual annotation, which means that not only multi-view features are often missing, and label completeness is also difficult to be satisfied. To deal with the double incomplete multi-view multi-label classification problem, we propose a deep instance-level contrastive network, namely DICNet. Different from conventional methods, our DICNet focuses on leveraging deep neural network to exploit the high-level semantic representations of samples rather than shallow-level features. First, we utilize the stacked autoencoders to build an end-to-end multi-view feature extraction framework to learn the view-specific representations of samples. Furthermore, in order to improve the consensus representation ability, we introduce an incomplete instance-level contrastive learning scheme to guide the encoders to better extract the consensus information of multiple views and use a multi-view weighted fusion module to enhance the discrimination of semantic features. Overall, our DICNet is adept in capturing consistent discriminative representations of multi-view multi-label data and avoiding the negative effects of missing views and missing labels. Extensive experiments performed on five datasets validate that our method outperforms other state-of-the-art methods.

Low-Rank Tensor Based Proximity Learning for Multi-View Clustering

Graph-oriented multi-view clustering methods have achieved impressive performances by employing relationships and complex structures hidden in multi-view data. However, most of them still suffer from the following two common problems. (1) They target at studying a common representation or pairwise correlations between views, neglecting the comprehensiveness and deeper higher-order correlations among multiple views. (2) The prior knowledge of view-specific representation can not be taken into account to obtain the consensus indicator graph in a unified graph construction and clustering framework. To deal with these problems, we propose a novel Low-rank Tensor Based Proximity Learning (LTBPL) approach for multi-view clustering, where multiple low-rank probability affinity matrices and consensus indicator graph reflecting the final performances are jointly studied in a unified framework. Specifically, multiple affinity representations are stacked in a low-rank constrained tensor to recover their comprehensiveness and higher-order correlations. Meanwhile, view-specific representation carrying different adaptive confidences is jointly linked with the consensus indicator graph. Extensive experiments on nine real-world datasets indicate the superiority of LTBPL compared with the state-of-the-art methods.

Learning enhanced specific representations for multi-view feature learning

Multi-view data has two basic characteristics: consensus property and complementary property, in which complementary information refers to all view-specific information. Inspired by the popular saying “The whole is greater than the sum of its parts”, we introduce the concepts of “parts”, “sum of its parts” and “whole” into multi-view feature learning. When view-specific information is regarded as the “parts”, the complementary information consisting of all view-specific information would correspond to the ”sum of its parts”. To explore the “whole” information, we propose the Learning Enhanced Specific Representations for Multi-view Feature Learning (MvESR) approach, which points to learning the enhanced view-specific information through beneficial interactions between views. Specifically, MvESR concatenates all view-specific representations as the “sum” information. Based on the “sum” information, MvESR obtains the enhanced view-specific information through an element-wise addition between view-specific representation and the “sum” representation. Then the complementary information consisting of enhanced view-specific representations can be regarded as the “whole”. In addition, MvESR obtains cross-view consensus information between each pairwise views, then concatenates them as fused cross-view consensus information. Considering that different representations may have different contributions for classification, we design an adaptive-weighting loss fusion strategy for multi-view classification. Experimental results on six large-scale public datasets verify that the proposed approach outperforms the compared methods.

Multi-view unsupervised feature selection with tensor robust principal component analysis and consensus graph learning

Recently, multi-view unsupervised feature selection has attracted much attention due to its efficiency and better interpretability in processing high-dimensional multi-view datasets. Most existing methods rely on the constructed similarity matrices to obtain reliable pseudo labels to guide the feature selection. However, the considerable adverse noise in the raw data inevitably impedes the exploration of true underlying similarity structures. Besides, the inter-view correlations are often ignored during the common representation learning, which limits the effective fusion of the essential information from multiple views. To solve these issues, we design a novel robust multi-view unsupervised feature selection framework. Specifically, our method seeks a set of noise-free view-specific similarity matrices by leveraging tensor robust principal component analysis, where the high-order connections among different views are well exploited through the constructed low-rank tensor. Meanwhile, a high-quality consensus similarity matrix is adaptively learned from the view-specific representations within the same unified framework to capture the shared local structures. To enhance the discriminative ability of the feature selection matrix, we further impose a rank constraint on the consensus similarity matrix to obtain reliable pseudo cluster indicators. We present an efficient optimization algorithm ground on the alternating direction method of multipliers to solve the proposed model. Experimental results on six multi-view datasets confirm the superiority of our method.

Facilitated low-rank multi-view subspace clustering

Low-rank multi-view subspace clustering has recently attracted increasing attention in the multi-view learning research. Despite significant progress, most existing approaches still suffer from two issues. First, they mostly focus on exploiting the low-rank consistency across multiple views, but often ignore the low-rank structure within each view. Second, they often encounter the expensive time overhead, typically owing to the costs of matrix inversion and singular value decomposition (SVD) at each iteration. In light of this, we propose an efficient and effective approach termed Facilitated Low-rank Multi-view Subspace Clustering (FLMSC) in this paper. In terms of efficiency, our approach factorizes the view-specific representation matrix into two small factor matrices, i.e., an orthogonal dictionary and a latent representation, which mitigates the computation cost of solving SVD problems. In terms of effectiveness, our approach preserves the latent low-rank structure within each view, while at the same time encourages the structural consistency across different views by imposing an agreement term. Based on this, our approach can fully explore the underlying subspace structure of multiple views, so as to better serve for the following spectral clustering. Besides, a facilitated iterative algorithm is developed for the resultant optimization problem, upon which the matrix inversion operation is substantially accelerated during iterations. Experimental results on a variety of multi-view data sets demonstrate the effectiveness and efficiency of our approach. The source code and data sets are available at: https://www.researchgate.net/publication/365349930_FLMSC_v1.

Instance-wise multi-view representation learning

Multi-view representation learning aims to integrate multiple data information from different views to improve the task performance. The information contained in multi-view data is usually complex. Not only do different views contain different information, but also different samples of the same view contain different information. In the multi-view representation learning, most existing methods either simply treat each view/sample with equal importance, or set fixed or dynamic weights for different views/samples, which is not accurate enough to capture the information of dimensions of each sample and causes information redundancy, especially for high-dimensional samples. In this paper, we propose a novel unsupervised multi-view representation learning method based on instance-wise feature selection. A main advantage of instance-wise feature selection in this paper is that one can dynamically select dimensions that favor both view-specific representation learning and view-shared representation learning for each sample, thereby improving the performance from the perspective of model input. The proposed method consists of selector network, view-specific network and view-shared network. Specifically, selector network is used to obtain the selection template, which selects different number of dimensions conducive to representation learning from different samples to solve the sample heterogeneity problem; the view-specific network and view-shared network are used to extract the view-specific and view-shared representations, respectively. The selector network, view-shared network, and view-specific network are optimized alternately. Extensive experiments on various multi-view datasets with clustering and multi-label classification tasks demonstrate that the proposed method outperforms the state-of-the-art multi-view learning methods.

Multiview Graph Restricted Boltzmann Machines.

Recently, the restricted Boltzmann machine (RBM) has aroused considerable interest in the multiview learning field. Although effectiveness is observed, like many existing multiview learning models, multiview RBM ignores the local manifold structure of multiview data. In this article, we first propose a novel graph RBM model, which preserves the data manifold structure and is amenable to Gibbs sampling. Then, we develop a multiview graph RBM model on the basis of the graph RBM, which performs local structural learning and multiview representation learning simultaneously. The proposed multiview model has the following merits: 1) it preserves the data manifold structure for multiview classification and 2) it performs view-consistent representation learning and view-specific representation learning simultaneously. The experimental results show that the proposed multiview model outperforms other state-of-the-art multiview classification algorithms.

Elucidating tumor heterogeneity from spatially resolved transcriptomics data by multi-view graph collaborative learning

Spatially resolved transcriptomics (SRT) technology enables us to gain novel insights into tissue architecture and cell development, especially in tumors. However, lacking computational exploitation of biological contexts and multi-view features severely hinders the elucidation of tissue heterogeneity. Here, we propose stMVC, a multi-view graph collaborative-learning model that integrates histology, gene expression, spatial location, and biological contexts in analyzing SRT data by attention. Specifically, stMVC adopting semi-supervised graph attention autoencoder separately learns view-specific representations of histological-similarity-graph or spatial-location-graph, and then simultaneously integrates two-view graphs for robust representations through attention under semi-supervision of biological contexts. stMVC outperforms other tools in detecting tissue structure, inferring trajectory relationships, and denoising on benchmark slices of human cortex. Particularly, stMVC identifies disease-related cell-states and their transition cell-states in breast cancer study, which are further validated by the functional and survival analysis of independent clinical data. Those results demonstrate clinical and prognostic applications from SRT data.

MMatch: Semi-Supervised Discriminative Representation Learning for Multi-View Classification

Semi-supervised multi-view learning has been an important research topic due to its capability to exploit complementary information from unlabeled multi-view data. This work proposes MMatch, a new semi-supervised discriminative representation learning method for multi-view classification. Unlike existing multi-view representation learning methods that seldom consider the negative impact caused by particular views with unclear classification structures (weak discriminative views). MMatch jointly learns view-specific representations and class probabilities of training data. The representations concatenated to integrate multiple views’ information to form a global representation. Moreover, MMatch performs the smoothness constraint on the class probabilities of the global representation to improve pseudo labels, whereas the pseudo labels regularize the structure of view-specific representations. A discriminative global representation is mined with the training process, and the negative impact of weak discriminative views is overcome. Besides, MMatch learns consistent classification while preserving diverse information from multiple views. Experiments on several multi-view datasets demonstrate the effectiveness of MMatch.

Tensor-based multi-view clustering with consistency exploration and diversity regularization

How to make good use of information from all views is the core problem in multi-view clustering (MVC), and widely recognized experience of attaining this goal is to leverage consistent and complementary principles. However, current methods do not take full advantage of these two principles. On the one hand, some existing methods ignore the connection between multiple views and the influence of manifold information on consensus representation. On the other hand, some others simply sum all the view-specific representations together as the final representation, which result in insufficient mining of complementary information. In this manuscript, we propose a novel tensor-based multi-view clustering approach that significantly improves consistency exploration and diversity capturing. In particular, we utilize the low-rank tensor learning with tensor-based singular value decomposition (t-SVD), aiming at capturing the correlations among different views. Moreover, we further split the low-rank tensor into a consistent matrix and a set of view-specific matrices, where the former is responsible for exploring the common manifold information via graph regularization, and the latter is used to mine complementary information through learning the view-specific representations as various as possible. We integrate low-rank tensor learning, consistency exploration and diversity regularization into a whole framework and use an alternating direction minimization strategy to optimize it. Experiments conducted on eight benchmark datasets show that our approach gains superior performance over several state-of-the-arts.

Tensorial Multiview Subspace Clustering for Polarimetric Hyperspectral Images

Polarimetric hyperspectral images (PHSI) can provide complementary representations of a scene from the perspectives of images, spectra and polarization at the same time, and are expected to improve the quality of scene description. In this paper, the clustering for PHSI is deemed to be a multi-view clustering task, and a tensorial polarimetric-spectral multi-view subspace clustering (TPS-MSC) algorithm for PHSI is proposed. It constructs a small size dictionary, instead of a large self-representative dictionary, by pre-clustering each view independently to give a sparse representation of all the data. Then the view-specific representation matrices are tensorized to explore the low-rank structure among different views, and the consistency of all views in pre-clustering is incorporated into the representation learning framework to strengthen the inter-view correlations. The proposed model is efficiently optimized by the alternative direction minimization of multipliers (ADMM) algorithm. Some experiments are carried out to validate the capacity of PHSI for target identification, and to demonstrate the accuracy and efficiency of the proposed TPS-MSC algorithm.

Multiview Common Subspace Clustering via Coupled Low Rank Representation

Multi-view subspace clustering (MVSC) finds a shared structure in latent low-dimensional subspaces of multi-view data to enhance clustering performance. Nonetheless, we observe that most existing MVSC methods neglect the diversity in multi-view data by considering only the common knowledge to find a shared structure either directly or by merging different similarity matrices learned for each view. In the presence of noise, this predefined shared structure becomes a biased representation of the different views. Thus, in this article, we propose a MVSC method based on coupled low-rank representation to address the above limitation. Our method first obtains a low-rank representation for each view, constrained to be a linear combination of the view-specific representation and the shared representation by simultaneously encouraging the sparsity of view-specific one. Then, it uses the k -block diagonal regularizer to learn a manifold recovery matrix for each view through respective low-rank matrices to recover more manifold structures from them. In this way, the proposed method can find an ideal similarity matrix by approximating clustering projection matrices obtained from the recovery structures. Hence, this similarity matrix denotes our clustering structure with exactly k connected components by applying a rank constraint on the similarity matrix’s relaxed Laplacian matrix to avoid spectral post-processing of the low-dimensional embedding matrix. The core of our idea is such that we introduce dynamic approximation into the low-rank representation to allow the clustering structure and the shared representation to guide each other to learn cleaner low-rank matrices that would lead to a better clustering structure. Therefore, our approach is notably different from existing methods in which the local manifold structure of data is captured in advance. Extensive experiments on six benchmark datasets show that our method outperforms 10 similar state-of-the-art compared methods in six evaluation metrics.