Progressive Neighbor-masked Contrastive Learning for Fusion-style Deep Multi-view Clustering.

Fusion-style Deep Multi-view Clustering (FDMC) can efficiently integrate comprehensive feature information from latent embeddings of multiple views and has drawn much attention recently. However, existing FDMC methods suffer from the interference of view-specific information for fusion representation, affecting the learning of discriminative cluster structure. In this paper, we propose a new framework of Progressive Neighbor-masked Contrastive Learning for FDMC (PNCL-FDMC) to tackle the aforementioned issues. Specifically, by using neighbor-masked contrastive learning, PNCL-FDMC can explicitly maintain the local structure during the embedding aggregation, which is beneficial to the common semantics enhancement on the fusion view. Based on the consistent aggregation, the fusion view is further enhanced by diversity-aware cluster structure enhancement. In this process, the enhanced cluster assignments and cluster discrepancies are employed to guide the weighted neighbor-masked contrastive alignment of semantic structure between individual views and the fusion view. Extensive experiments validate the effectiveness of the proposed framework, revealing its ability in discriminative representation learning and improving clustering performance.

A Multitask Network Robustness Analysis System Based on the Graph Isomorphism Network.

Despite various measures across different engineering and social systems, network robustness remains crucial for resisting random faults and malicious attacks. In this study, robustness refers to the ability of a network to maintain its functionality after a part of the network has failed. Existing methods assess network robustness using attack simulations, spectral measures, or deep neural networks (DNNs), which return a single metric as a result. Evaluating network robustness is technically challenging, while evaluating a single metric is practically insufficient. This article proposes a multitask analysis system based on the graph isomorphism network (GIN) model, abbreviated as GIN-MAS. First, a destruction-based robustness metric is formulated using the destruction threshold of the examined network. A multitask learning approach is taken to learn the network robustness metrics, including connectivity robustness, controllability robustness, destruction threshold, and the maximum number of connected components. Then, a five-layer GIN is constructed for evaluating the aforementioned four robustness metrics simultaneously. Finally, extensive experimental studies reveal that 1) GIN-MAS outperforms nine other methods, including three state-of-the-art convolutional neural network (CNN)-based robustness evaluators, with lower prediction errors for both known and unknown datasets from various directed and undirected, synthetic, and real-world networks; 2) the multitask learning scheme is not only capable of handling multiple tasks simultaneously but more importantly it enables the parameter and knowledge sharing across tasks, thus preventing overfitting and enhancing the performances; and 3) GIN-MAS performs multitasks significantly faster than other single-task evaluators. The excellent performance of GIN-MAS suggests that more powerful DNNs have great potentials for analyzing more complicated and comprehensive robustness evaluation tasks.

Policy Iteration-Based Learning Design for Linear Continuous-Time Systems Under Initial Stabilizing OPFB Policy.

Policy iteration (PI), an iterative method in reinforcement learning, has the merit of interactions with a little-known environment to learn a decision law through policy evaluation and improvement. However, the existing PI-based results for output-feedback (OPFB) continuous-time systems relied heavily on an initial stabilizing full state-feedback (FSFB) policy. It thus raises the question of violating the OPFB principle. This article addresses such a question and establishes the PI under an initial stabilizing OPFB policy. We prove that an off-policy Bellman equation can transform any OPFB policy into an FSFB policy. Based on this transformation property, we revise the traditional PI by appending an additional iteration, which turns out to be efficient in approximating the optimal control under the initial OPFB policy. We show the effectiveness of the proposed learning methods through theoretical analysis and a case study.

Multimodal Fusion Network for 3-D Lane Detection.

3-D lane detection is a challenging task due to the diversity of lanes, occlusion, dazzle light, and so on. Traditional methods usually use highly specialized handcrafted features and carefully designed postprocessing to detect them. However, these methods are based on strong assumptions and single modal so that they are easily scalable and have poor performance. In this article, a multimodal fusion network (MFNet) is proposed through using multihead nonlocal attention and feature pyramid for 3-D lane detection. It includes three parts: multihead deformable transformation (MDT) module, multidirectional attention feature pyramid fusion (MA-FPF) module, and top-view lane prediction (TLP) ones. First, MDT is presented to learn and mine multimodal features from RGB images, depth maps, and point cloud data (PCD) for achieving optimal lane feature extraction. Then, MA-FPF is designed to fuse multiscale features for presenting the vanish of lane features as the network deepens. Finally, TLP is developed to estimate 3-D lanes and predict their position. Experimental results on the 3-D lane synthetic and ONCE-3DLanes datasets demonstrate that the performance of the proposed MFNet outperforms the state-of-the-art methods in both qualitative and quantitative analyses and visual comparisons.

Predicting drug-target interactions using matrix factorization with self-paced learning and dual similarity information.

BACKGROUND: Drug repositioning (DR) refers to a method used to find new targets for existing drugs. This method can effectively reduce the development cost of drugs, save time on drug development, and reduce the risks of drug design. The traditional experimental methods related to DR are time-consuming, expensive, and have a high failure rate. Several computational methods have been developed with the increase in data volume and computing power. In the last decade, matrix factorization (MF) methods have been widely used in DR issues. However, these methods still have some challenges. (1) The model easily falls into a bad local optimal solution due to the high noise and high missing rate in the data. (2) Single similarity information makes the learning power of the model insufficient in terms of identifying the potential associations accurately. OBJECTIVE: We proposed self-paced learning with dual similarity information and MF (SPLDMF), which introduced the self-paced learning method and more information related to drugs and targets into the model to improve prediction performance. METHODS: Combining self-paced learning first can effectively alleviate the model prone to fall into a bad local optimal solution because of the high noise and high data missing rate. Then, we incorporated more data into the model to improve the model's capacity for learning. RESULTS: Our model achieved the best results on each dataset tested. For example, the area under the receiver operating characteristic curve and the precision-recall curve of SPLDMF was 0.982 and 0.815, respectively, outperforming the state-of-the-art methods. CONCLUSION: The experimental results on five benchmark datasets and two extended datasets demonstrated the effectiveness of our approach in predicting drug-target interactions.

HGCLAMIR: Hypergraph contrastive learning with attention mechanism and integrated multi-view representation for predicting miRNA-disease associations.

Existing studies have shown that the abnormal expression of microRNAs (miRNAs) usually leads to the occurrence and development of human diseases. Identifying disease-related miRNAs contributes to studying the pathogenesis of diseases at the molecular level. As traditional biological experiments are time-consuming and expensive, computational methods have been used as an effective complement to infer the potential associations between miRNAs and diseases. However, most of the existing computational methods still face three main challenges: (i) learning of high-order relations; (ii) insufficient representation learning ability; (iii) importance learning and integration of multi-view embedding representation. To this end, we developed a HyperGraph Contrastive Learning with view-aware Attention Mechanism and Integrated multi-view Representation (HGCLAMIR) model to discover potential miRNA-disease associations. First, hypergraph convolutional network (HGCN) was utilized to capture high-order complex relations from hypergraphs related to miRNAs and diseases. Then, we combined HGCN with contrastive learning to improve and enhance the embedded representation learning ability of HGCN. Moreover, we introduced view-aware attention mechanism to adaptively weight the embedded representations of different views, thereby obtaining the importance of multi-view latent representations. Next, we innovatively proposed integrated representation learning to integrate the embedded representation information of multiple views for obtaining more reasonable embedding information. Finally, the integrated representation information was fed into a neural network-based matrix completion method to perform miRNA-disease association prediction. Experimental results on the cross-validation set and independent test set indicated that HGCLAMIR can achieve better prediction performance than other baseline models. Furthermore, the results of case studies and enrichment analysis further demonstrated the accuracy of HGCLAMIR and unconfirmed potential associations had biological significance.

Balanced Unfolding Induced Tensor Nuclear Norms for High-Order Tensor Completion.

The recently proposed tensor tubal rank has been witnessed to obtain extraordinary success in real-world tensor data completion. However, existing works usually fix the transform orientation along the third mode and may fail to turn multidimensional low-tubal-rank structure into account. To alleviate these bottlenecks, we introduce two unfolding induced tensor nuclear norms (TNNs) for the tensor completion (TC) problem, which naturally extends tensor tubal rank to high-order data. Specifically, we show how multidimensional low-tubal-rank structure can be captured by utilizing a novel balanced unfolding strategy, upon which two TNNs, namely, overlapped TNN (OTNN) and latent TNN (LTNN), are developed. We also show the immediate relationship between the tubal rank of unfolding tensor and the existing tensor network (TN) rank, e.g., CANDECOMP/PARAFAC (CP) rank, Tucker rank, and tensor ring (TR) rank, to demonstrate its efficiency and practicality. Two efficient TC models are then proposed with theoretical guarantees by analyzing a unified nonasymptotic upper bound. To solve optimization problems, we develop two alternating direction methods of multipliers (ADMM) based algorithms. The proposed models have been demonstrated to exhibit superior performance based on experimental findings involving synthetic and real-world tensors, including facial images, light field images, and video sequences.

An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments.

The BeiDou Navigation Satellite System (BDS) provides real-time absolute location services to users around the world and plays a key role in the rapidly evolving field of autonomous driving. In complex urban environments, the positioning accuracy of BDS often suffers from large deviations due to non-line-of-sight (NLOS) signals. Deep learning (DL) methods have shown strong capabilities in detecting complex and variable NLOS signals. However, these methods still suffer from the following limitations. On the one hand, supervised learning methods require labeled samples for learning, which inevitably encounters the bottleneck of difficulty in constructing databases with a large number of labels. On the other hand, the collected data tend to have varying degrees of noise, leading to low accuracy and poor generalization performance of the detection model, especially when the environment around the receiver changes. In this article, we propose a novel deep neural architecture named convolutional denoising autoencoder network (CDAENet) to detect NLOS in urban forest environments. Specifically, we first design a denoising autoencoder based on unsupervised DL to reduce the long time series signal dimension and extract the deep features of the data. Meanwhile, denoising autoencoders improve the model's robustness in identifying noisy data by introducing a certain amount of noise into the input data. Then, an MLP algorithm is used to identify the non-linearity of the BDS signal. Finally, the performance of the proposed CDAENet model is validated on a real urban forest dataset. The experimental results show that the satellite detection accuracy of our proposed algorithm is more than 95%, which is about an 8% improvement over existing machine-learning-based methods and about 3% improvement over deep-learning-based approaches.

Digital image correlation-assisted phase-sensitive optical coherence tomography.

In this Letter, we introduce a digital image correlation-assisted (DIC-assisted) method to tackle the challenges of phase decorrelation and the inability to measure lateral displacement in phase-sensitive optical coherence tomography (PhS-OCT). This DIC-assisted PhS-OCT (DIC-PhS-OCT) first employs DIC to track displacements from the measured amplitude spectra and subsequently uses these tracked displacements to correct supra-pixel displacement offsets in the measured phase spectra. As a result, it effectively mitigates phase decorrelation resulting from both axial and lateral displacements while enabling the acquisition of sub-pixel-level lateral displacements during the DIC computation. Our experiments demonstrate the effectiveness of DIC-PhS-OCT in addressing these challenges while retaining the ultrahigh sensitivity of conventional PhS-OCT.

Dual-convolutional neural network-enhanced strain estimation method for optical coherence elastography.

Strain estimation is vital in phase-sensitive optical coherence elastography (PhS-OCE). In this Letter, we introduce a novel, to the best of our knowledge, method to improve strain estimation by using a dual-convolutional neural network (Dual-CNN). This approach requires two sets of PhS-OCE systems: a high-resolution system for high-quality training data and a cost-effective standard-resolution system for practical measurements. During training, high-resolution strain results acquired from the former system and the pre-existing strain estimation CNN serve as label data, while the narrowed light source-acquired standard-resolution phase results act as input data. By training a new network with this data, high-quality strain results can be estimated from standard-resolution PhS-OCE phase results. Comparison experiments show that the proposed Dual-CNN can preserve the strain quality even when the light source bandwidth is reduced by over 80%.

Random Online Hashing for Cross-Modal Retrieval.

In the past decades, supervised cross-modal hashing methods have attracted considerable attentions due to their high searching efficiency on large-scale multimedia databases. Many of these methods leverage semantic correlations among heterogeneous modalities by constructing a similarity matrix or building a common semantic space with the collective matrix factorization method. However, the similarity matrix may sacrifice the scalability and cannot preserve more semantic information into hash codes in the existing methods. Meanwhile, the matrix factorization methods cannot embed the main modality-specific information into hash codes. To address these issues, we propose a novel supervised cross-modal hashing method called random online hashing (ROH) in this article. ROH proposes a linear bridging strategy to simplify the pair-wise similarities factorization problem into a linear optimization one. Specifically, a bridging matrix is introduced to establish a bidirectional linear relation between hash codes and labels, which preserves more semantic similarities into hash codes and significantly reduces the semantic distances between hash codes of samples with similar labels. Additionally, a novel maximum eigenvalue direction (MED) embedding method is proposed to identify the direction of maximum eigenvalue for the original features and preserve critical information into modality-specific hash codes. Eventually, to handle real-time data dynamically, an online structure is adopted to solve the problem of dealing with new arrival data chunks without considering pairwise constraints. Extensive experimental results on three benchmark datasets demonstrate that the proposed ROH outperforms several state-of-the-art cross-modal hashing methods.

Comprehensive Multiview Representation Learning via Deep Autoencoder-Like Nonnegative Matrix Factorization.

Learning a comprehensive representation from multiview data is crucial in many real-world applications. Multiview representation learning (MRL) based on nonnegative matrix factorization (NMF) has been widely adopted by projecting high-dimensional space into a lower order dimensional space with great interpretability. However, most prior NMF-based MRL techniques are shallow models that ignore hierarchical information. Although deep matrix factorization (DMF)-based methods have been proposed recently, most of them only focus on the consistency of multiple views and have cumbersome clustering steps. To address the above issues, in this article, we propose a novel model termed deep autoencoder-like NMF for MRL (DANMF-MRL), which obtains the representation matrix through the deep encoding stage and decodes it back to the original data. In this way, through a DANMF-based framework, we can simultaneously consider the multiview consistency and complementarity, allowing for a more comprehensive representation. We further propose a one-step DANMF-MRL, which learns the latent representation and final clustering labels matrix in a unified framework. In this approach, the two steps can negotiate with each other to fully exploit the latent clustering structure, avoid previous tedious clustering steps, and achieve optimal clustering performance. Furthermore, two efficient iterative optimization algorithms are developed to solve the proposed models both with theoretical convergence analysis. Extensive experiments on five benchmark datasets demonstrate the superiority of our approaches against other state-of-the-art MRL methods.

Dynamic sparse coding-based value estimation network for deep reinforcement learning.

Deep Reinforcement Learning (DRL) is one powerful tool for varied control automation problems. Performances of DRL highly depend on the accuracy of value estimation for states from environments. However, the Value Estimation Network (VEN) in DRL can be easily influenced by the phenomenon of catastrophic interference from environments and training. In this paper, we propose a Dynamic Sparse Coding-based (DSC) VEN model to obtain precise sparse representations for accurate value prediction and sparse parameters for efficient training, which is not only applicable in Q-learning structured discrete-action DRL but also in actor-critic structured continuous-action DRL. In detail, to alleviate interference in VEN, we propose to employ DSC to learn sparse representations for accurate value estimation with dynamic gradients beyond the conventional ℓ1 norm that provides same-value gradients. To avoid influences from redundant parameters, we employ DSC to prune weights with dynamic thresholds more efficiently than static thresholds like ℓ1 norm. Experiments demonstrate that the proposed algorithms with dynamic sparse coding can obtain higher control performances than existing benchmark DRL algorithms in both discrete-action and continuous-action environments, e.g., over 25% increase in Puddle World and about 10% increase in Hopper. Moreover, the proposed algorithm can reach convergence efficiently with fewer episodes in different environments.

Integration of multi-omics data using adaptive graph learning and attention mechanism for patient classification and biomarker identification.

With the rapid development and accumulation of high-throughput sequencing technology and omics data, many studies have conducted a more comprehensive understanding of human diseases from a multi-omics perspective. Meanwhile, graph-based methods have been widely used to process multi-omics data due to its powerful expressive ability. However, most existing graph-based methods utilize fixed graphs to learn sample embedding representations, which often leads to sub-optimal results. Furthermore, treating embedding representations of different omics equally usually cannot obtain more reasonable integrated information. In addition, the complex correlation between omics is not fully taken into account. To this end, we propose an end-to-end interpretable multi-omics integration method, named MOGLAM, for disease classification prediction. Dynamic graph convolutional network with feature selection is first utilized to obtain higher quality omic-specific embedding information by adaptively learning the graph structure and discover important biomarkers. Then, multi-omics attention mechanism is applied to adaptively weight the embedding representations of different omics, thereby obtaining more reasonable integrated information. Finally, we propose omic-integrated representation learning to capture complex common and complementary information between omics while performing multi-omics integration. Experimental results on three datasets show that MOGLAM achieves superior performance than other state-of-the-art multi-omics integration methods. Moreover, MOGLAM can identify important biomarkers from different omics data types in an end-to-end manner.

GDCL-NcDA: identifying non-coding RNA-disease associations via contrastive learning between deep graph learning and deep matrix factorization.

Non-coding RNAs (ncRNAs) draw much attention from studies widely in recent years because they play vital roles in life activities. As a good complement to wet experiment methods, computational prediction methods can greatly save experimental costs. However, high false-negative data and insufficient use of multi-source information can affect the performance of computational prediction methods. Furthermore, many computational methods do not have good robustness and generalization on different datasets. In this work, we propose an effective end-to-end computing framework, called GDCL-NcDA, of deep graph learning and deep matrix factorization (DMF) with contrastive learning, which identifies the latent ncRNA-disease association on diverse multi-source heterogeneous networks (MHNs). The diverse MHNs include different similarity networks and proven associations among ncRNAs (miRNAs, circRNAs, and lncRNAs), genes, and diseases. Firstly, GDCL-NcDA employs deep graph convolutional network and multiple attention mechanisms to adaptively integrate multi-source of MHNs and reconstruct the ncRNA-disease association graph. Then, GDCL-NcDA utilizes DMF to predict the latent disease-associated ncRNAs based on the reconstructed graphs to reduce the impact of the false-negatives from the original associations. Finally, GDCL-NcDA uses contrastive learning (CL) to generate a contrastive loss on the reconstructed graphs and the predicted graphs to improve the generalization and robustness of our GDCL-NcDA framework. The experimental results show that GDCL-NcDA outperforms highly related computational methods. Moreover, case studies demonstrate the effectiveness of GDCL-NcDA in identifying the associations among diversiform ncRNAs and diseases.

Cross-modal hashing with missing labels.

Hashing-based cross-modal retrieval methods have become increasingly popular due to their advantages in storage and speed. While current methods have demonstrated impressive results, there are still several issues that have not been addressed. Specifically, many of these approaches assume that labels are perfectly assigned, despite the fact that in real-world scenarios, labels are often incomplete or partially missing. There are two reasons for this, as manual labeling can be a complex and time-consuming task, and annotators may only be interested in certain objects. As such, cross-modal retrieval with missing labels is a significant challenge that requires further attention. Moreover, the similarity between labels is frequently ignored, which is important for exploring the high-level semantics of labels. To address these limitations, we propose a novel method called Cross-Modal Hashing with Missing Labels (CMHML). Our method consists of several key components. First, we introduce Reliable Label Learning to preserve reliable information from the observed labels. Next, to infer the uncertain part of the predicted labels, we decompose the predicted labels into latent representations of labels and samples. The representation of samples is extracted from different modalities, which assists in inferring missing labels. We also propose Label Correlation Preservation to enhance the similarity between latent representations of labels. Hash codes are then learned from the representation of samples through Global Approximation Learning. We also construct a similarity matrix according to predicted labels and embed it into hash codes learning to explore the value of labels. Finally, we train linear classifiers to map original samples to a low-dimensional Hamming space. To evaluate the efficacy of CMHML, we conduct extensive experiments on four publicly available datasets. Our method is compared to other state-of-the-art methods, and the results demonstrate that our model performs competitively even when most labels are missing.

High-resolution optical coherence tomography using gapped spectrum and real-valued iterative adaptive approach.

Optical coherence tomography (OCT) is a powerful imaging technique that is capable of imaging cross-sectional structures with micrometer resolution. After combining with phase-sensitive detection, it can sense small changes in the physical quantities inside an object. In OCT, axial resolution is generally improved by expanding the bandwidth of the light source. However, when the bandwidth is expanded discontinuously, the wavelength gap induces abnormal sidelobes when estimating OCT signals in the depth domain. This problem can lead to poor axial resolution. Herein, we present a method based on a real-valued iterative adaptive approach (RIAA) to achieve a high axial resolution under a discontinuous bandwidth condition. The method uses a weighted matrix to suppress the abnormal sidelobes caused by the wavelength gap and, therefore, can realize high-resolution measurements. A single-reflector OCT spectrum was first measured for validation, and its amplitude in the depth domain was estimated using different methods. The results indicate that the RIAA had the best capability of suppressing abnormal sidelobes, thereby achieving a high axial resolution. In addition, cross-sectional images and phase-difference maps of three different samples were measured. A comparison of the results validated the practical value of this method.

Deep learning-based weak micro-defect detection on an optical lens surface with micro vision.

To solve limited efficiency and reliability issues caused by current manual quality control processes in optical lens (OL) production environments, we propose an automatic micro vision-based inspection system named MVIS used to capture the surface defect images and make the OL dataset and predictive inference. Because of low resolution and recognition, OL defects are weak, due to their ambiguous morphology and micro size, making a poor detection effect for the existing method. A deep-learning algorithm for a weak micro-defect detector named ISE-YOLO is proposed, making the best for deep layers, utilizing the ISE attention mechanism module in the neck, and introducing a novel class loss function to extract richer semantics from convolution layers and learning more information. Experimental results on the OL dataset show that ISE-YOLO demonstrates a better performance, with the mean average precision, recall, and F1 score increasing by 3.62%, 6.12% and 3.07% respectively, compared to the YOLOv5. In addition, compared with YOLOv7, which is the latest version of YOLO serials, the mean average precision of ISE-YOLO is improved by 2.58%, the weight size is decreased by more than 30% and the speed is increased by 16%.

Direct-Optimization-Based DC Dictionary Learning With the MCP Regularizer.

Direct-optimization-based dictionary learning has attracted increasing attention for improving computational efficiency. However, the existing direct optimization scheme can only be applied to limited dictionary learning problems, and it remains an open problem to prove that the whole sequence obtained by the algorithm converges to a critical point of the objective function. In this article, we propose a novel direct-optimization-based dictionary learning algorithm using the minimax concave penalty (MCP) as a sparsity regularizer that can enforce strong sparsity and obtain accurate estimation. For solving the corresponding optimization problem, we first decompose the nonconvex MCP into two convex components. Then, we employ the difference of the convex functions algorithm and the nonconvex proximal-splitting algorithm to process the resulting subproblems. Thus, the direct optimization approach can be extended to a broader class of dictionary learning problems, even if the sparsity regularizer is nonconvex. In addition, the convergence guarantee for the proposed algorithm can be theoretically proven. Our numerical simulations demonstrate that the proposed algorithm has good convergence performances in different cases and robust dictionary-recovery capabilities. When applied to sparse approximations, the proposed approach can obtain sparser and less error estimation than the different sparsity regularizers in existing methods. In addition, the proposed algorithm has robustness in image denoising and key-frame extraction.

Robust to Rank Selection: Low-Rank Sparse Tensor-Ring Completion.

Tensor-ring (TR) decomposition was recently studied and applied for low-rank tensor completion due to its powerful representation ability of high-order tensors. However, most of the existing TR-based methods tend to suffer from deterioration when the selected rank is larger than the true one. To address this issue, this article proposes a new low-rank sparse TR completion method by imposing the Frobenius norm regularization on its latent space. Specifically, we theoretically establish that the proposed method is capable of exploiting the low rankness and Kronecker-basis-representation (KBR)-based sparsity of the target tensor using the Frobenius norm of latent TR-cores. We optimize the proposed TR completion by block coordinate descent (BCD) algorithm and design a modified TR decomposition for the initialization of this algorithm. Extensive experimental results on synthetic data and visual data have demonstrated that the proposed method is able to achieve better results compared to the conventional TR-based completion methods and other state-of-the-art methods and, meanwhile, is quite robust even if the selected TR-rank increases.