Joint Projection Learning and Tensor Decomposition-Based Incomplete Multiview Clustering.

Incomplete multiview clustering (IMVC) has received increasing attention since it is often that some views of samples are incomplete in reality. Most existing methods learn similarity subgraphs from original incomplete multiview data and seek complete graphs by exploring the incomplete subgraphs of each view for spectral clustering. However, the graphs constructed on the original high-dimensional data may be suboptimal due to feature redundancy and noise. Besides, previous methods generally ignored the graph noise caused by the interclass and intraclass structure variation during the transformation of incomplete graphs and complete graphs. To address these problems, we propose a novel joint projection learning and tensor decomposition (JPLTD)-based method for IMVC. Specifically, to alleviate the influence of redundant features and noise in high-dimensional data, JPLTD introduces an orthogonal projection matrix to project the high-dimensional features into a lower-dimensional space for compact feature learning. Meanwhile, based on the lower-dimensional space, the similarity graphs corresponding to instances of different views are learned, and JPLTD stacks these graphs into a third-order low-rank tensor to explore the high-order correlations across different views. We further consider the graph noise of projected data caused by missing samples and use a tensor-decomposition-based graph filter for robust clustering. JPLTD decomposes the original tensor into an intrinsic tensor and a sparse tensor. The intrinsic tensor models the true data similarities. An effective optimization algorithm is adopted to solve the JPLTD model. Comprehensive experiments on several benchmark datasets demonstrate that JPLTD outperforms the state-of-the-art methods. The code of JPLTD is available at https://github.com/weilvNJU/JPLTD.

Predicting Label Distribution From Tie-Allowed Multi-Label Ranking.

Label distribution offers more information about label polysemy than logical label. There are presently two approaches to obtaining label distributions: LDL (label distribution learning) and LE (label enhancement). In LDL, experts must annotate training instances with label distributions, and a predictive function is trained on this training set to obtain label distributions. In LE, experts must annotate instances with logical labels, and label distributions are recovered from them. However, LDL is limited by expensive annotations, and LE has no performance guarantee. Therefore, we investigate how to predict label distribution from TMLR (tie-allowed multi-label ranking) which is a compromise on annotation cost but has good performance guarantees. On the one hand, we theoretically dissect the relationship between TMLR and label distribution. We define EAE (expected approximation error) to quantify the quality of an annotation, provide EAE bounds for TMLR, and derive the optimal range of label distributions corresponding to a given TMLR annotation. On the other hand, we propose a framework for predicting label distribution from TMLR via conditional Dirichlet mixtures. This framework blends the procedures of recovering and learning label distributions end-to-end and allows us to effortlessly encode our knowledge by a semi-adaptive scoring function. Extensive experiments validate our proposal.

TranSDFNet: Transformer-Based Truncated Signed Distance Fields for the Shape Design of Removable Partial Denture Clasps.

The ever-growing aging population has led to an increasing need for removable partial dentures (RPDs) since they are typically the least expensive treatment options for partial edentulism. However, the digital design of RPDs remains challenging for dental technicians due to the variety of partially edentulous scenarios and complex combinations of denture components. To accelerate the design of RPDs, we propose a U-shape network incorporated with Transformer blocks to automatically generate RPD clasps, one of the most frequently used RPD components. Unlike existing dental restoration design algorithms, we introduce the voxel-based truncated signed distance field (TSDF) as an intermediate representation, which reduces the sensitivity of the network to resolution and contributes to more smooth reconstruction. Besides, a selective insertion scheme is proposed for solving the memory issue caused by Transformer blocks and enables the algorithm to work well in scenarios with insufficient data. We further design two weighted loss functions to filter out the noisy signals generated from the zero-gradient areas in TSDF. Ablation and comparison studies demonstrate that our algorithm outperforms state-of-the-art reconstruction methods by a large margin and can serve as an intelligent auxiliary in denture design.

Adaptive Weighted Ranking-Oriented Label Distribution Learning.

Label distribution learning (LDL) is a novel machine-learning paradigm generalized from multilabel learning (MLL). LDL attaches a label distribution to each instance, giving the description degree of different labels. In many real-world applications, key labels, that is, labels with relatively higher description degrees, are preferable to be better predicted. Unfortunately, existing LDL metrics measure the distance or similarity between label distributions from a global perspective, failing to give sufficient attention to key labels. Therefore, we design a novel LDL metric, the description-degree percentile average (DPA), which simultaneously integrates both the exact ranking value and the description degree of each label. The DPA can enhance accuracy in predicting key labels. Furthermore, noting the shape characteristics of the label distributions, we minimize the variance distance between the predicted and the ground-truth label distributions, to better maintain the distinguishability of labels. Finally, we propose an adaptive weighted ranking-oriented LDL algorithm, which is more suitable for realistic LDL problems that require higher accuracy in predicting key labels. We conduct extensive comparison experiments on various types of LDL datasets. Experimental results on both traditional and newly introduced metrics demonstrate the effectiveness of our proposal.

Three-Stage Semisupervised Cross-Modal Hashing With Pairwise Relations Exploitation.

Hashing methods have sparked a great revolution in cross-modal retrieval due to the low cost of storage and computation. Benefiting from the sufficient semantic information of labeled data, supervised hashing methods have shown better performance compared with unsupervised ones. Nevertheless, it is expensive and labor intensive to annotate the training samples, which restricts the feasibility of supervised methods in real applications. To deal with this limitation, a novel semisupervised hashing method, i.e., three-stage semisupervised hashing (TS3H) is proposed in this article, where both labeled and unlabeled data are seamlessly handled. Different from other semisupervised approaches that learn the pseudolabels, hash codes, and hash functions simultaneously, the new approach is decomposed into three stages as the name implies, in which all of the stages are conducted individually to make the optimization cost-effective and precise. Specifically, the classifiers of different modalities are learned via the provided supervised information to predict the labels of unlabeled data at first. Then, hash code learning is achieved with a simple but efficient scheme by unifying the provided and the newly predicted labels. To capture the discriminative information and preserve the semantic similarities, we leverage pairwise relations to supervise both classifier learning and hash code learning. Finally, the modality-specific hash functions are obtained by transforming the training samples to the generated hash codes. The new approach is compared with the state-of-the-art shallow and deep cross-modal hashing (DCMH) methods on several widely used benchmark databases, and the experiment results verify its efficiency and superiority.

Low-Rank Tensor Regularized Views Recovery for Incomplete Multiview Clustering.

In real applications, it is often that the collected multiview data contain missing views. Most existing incomplete multiview clustering (IMVC) methods cannot fully utilize the underlying information of missing data or sufficiently explore the consistent and complementary characteristics. In this article, we propose a novel Low-rAnk Tensor regularized viEws Recovery (LATER) method for IMVC, which jointly reconstructs and utilizes the missing views and learns multilevel graphs for comprehensive similarity discovery in a unified model. The missing views are recovered from a common latent representation, and the recovered views conversely improve the learning of shared patterns. Based on the shared subspace representations and recovered complete multiview data, the multilevel graphs are learned by self-representation to fully exploit the consistent and complementary information among views. Besides, a tensor nuclear norm regularizer is introduced to pursue the global low-rank property and explore the interview correlations. An alternating direction minimization algorithm is presented to optimize the proposed model. Moreover, a new initialization method is proposed to promote the effectiveness of our method for latent representation learning and missing data recovery. Extensive experiments demonstrate that our method outperforms the state-of-the-art approaches.

Multi-Class ASD Classification via Label Distribution Learning with Class-Shared and Class-Specific Decomposition.

The behavioral and cognitive deficits in autism spectrum disorder (ASD) patients are associated with abnormal brain function. The resting-state functional magnetic resonance imaging (rs-fMRI) is an effective non-invasive tool for revealing the brain dysfunction for ASD patients. However, most rs-fMRI based ASD diagnosis methods are developed for simple binary classification, instead of classification of multiple sub-types in ASD. Besides, they assume that the class boundary in ASD classification is crisp, whereas the symptoms of ASD sub-types are a continuum from mild to severe impairments in both social communication and restrictive repetitive behaviors/interests, and do not have crisp boundary between each other. To this end, we introduce label distribution learning (LDL) into multi-class ASD classification and propose LDL-CSCS under the LDL framework. Specifically, the label distribution is introduced to describe how individual disease labels correlate with the subject. In the learning crierion of LDL-CSCS, the label distribution is decomposed into the class-shared and class-specific components, in which the class-shared component records the common knowledge across all persons and the class-specific component records the specific information in each ASD sub-type. Low-rank constraint is imposed on the class-shared component whereas the group sparse constraint is imposed on the class-specific component, respectively. An Augmented Lagrange Method (ALM) is developed to find the optimal solution. The experimental results show that the proposed method for ASD diagnosis has superior classification performance, compared with some existing algorithms.

Consciousness Level and Recovery Outcome Prediction Using High-Order Brain Functional Connectivity Network.

Based on the neuroimaging data from a large set of acquired brain injury patients, we investigate the feasibility of using machine learning for automatic prediction of individual consciousness level. Rather than using the traditional Pearson's correlation-based brain functional network, which measures only the simple temporal synchronization of the BOLD signals from each pair of brain regions, we construct a high-order brain functional network that is capable of characterizing topographical information-based high-level functional associations among brain regions. In such a high-order brain network, each node represents the community of a brain region, described by a set of this region's low-order functional associations with other brain regions, and each edge characterizes topographical similarity between a pair of such communities. Experimental results show that the high-order brain functional network enables a significant better classification for consciousness level and recovery outcome prediction.