Higher-order neurodynamical equation for simplex prediction.

It is demonstrated that higher-order patterns beyond pairwise relations can significantly enhance the learning capability of existing graph-based models, and simplex is one of the primary form for graphically representing higher-order patterns. Predicting unknown (disappeared) simplices in real-world complex networks can provide us with deeper insights, thereby assisting us in making better decisions. Nevertheless, previous efforts to predict simplices suffer from two issues: (i) they mainly focus on 2- or 3-simplices, and there are few models available for predicting simplices of arbitrary orders, and (ii) they lack the ability to analyze and learn the features of simplices from the perspective of dynamics. In this paper, we present a Higher-order Neurodynamical Equation for Simplex Prediction of arbitrary order (HNESP), which is a framework that combines neural networks and neurodynamics. Specifically, HNESP simulates the dynamical coupling process of nodes in simplicial complexes through different relations (i.e., strong pairwise relation, weak pairwise relation, and simplex) to learn node-level representations, while explaining the learning mechanism of neural networks from neurodynamics. To enrich the higher-order information contained in simplices, we exploit the entropy and normalized multivariate mutual information of different sub-structures of simplices to acquire simplex-level representations. Furthermore, simplex-level representations and multi-layer perceptron are used to quantify the existence probability of simplices. The effectiveness of HNESP is demonstrated by extensive simulations on seven higher-order benchmarks. Experimental results show that HNESP improves the AUC values of the state-of-the-art baselines by an average of 8.32%. Our implementations will be publicly available at: https://github.com/jianruichen/HNESP.

Toward Explainable Multiparty Learning: A Contrastive Knowledge Sharing Framework.

Multiparty learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multiparty learning approaches are confronted with obstacles, such as system heterogeneity, statistical heterogeneity, and incentive design. Determining how to deal with these challenges and further improve the efficiency and performance of multiparty learning has become an urgent problem to be solved. In this article, we propose a novel contrastive multiparty learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication and analogize multiparty learning as a many-to-one knowledge-sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets.

Multiobjective Multitasking Optimization With Decomposition-Based Transfer Selection.

Multiobjective multitasking optimization (MTO) needs to solve a set of multiobjective optimization problems simultaneously, and tries to speed up their solution by transferring useful search experiences across tasks. However, the quality of transfer solutions will significantly impact the transfer effect, which may even deteriorate the optimization performance with an improper selection of transfer solutions. To alleviate this issue, this article suggests a new multiobjective multitasking evolutionary algorithm (MMTEA) with decomposition-based transfer selection, called MMTEA-DTS. In this algorithm, all tasks are first decomposed into a set of subproblems, and then the transfer potential of each solution can be quantified based on the performance improvement ratio of its associated subproblem. Only high-potential solutions are selected to promote knowledge transfer. Moreover, to diversify the transfer of search experiences, a hybrid transfer evolution method is designed in this article. In this way, more diverse search experiences are transferred from high-potential solutions across different tasks to speed up their convergence. Three well-known benchmark suites suggested in the competition of evolutionary MTO and one real-world problem suite are used to verify the effectiveness of MMTEA-DTS. The experiments validate its advantages in solving most of the test problems when compared to five recently proposed MMTEAs.

Learning deep representation and discriminative features for clustering of multi-layer networks.

The multi-layer network consists of the interactions between different layers, where each layer of the network is depicted as a graph, providing a comprehensive way to model the underlying complex systems. The layer-specific modules of multi-layer networks are critical to understanding the structure and function of the system. However, existing methods fail to characterize and balance the connectivity and specificity of layer-specific modules in networks because of the complicated inter- and intra-coupling of various layers. To address the above issues, a joint learning graph clustering algorithm (DRDF) for detecting layer-specific modules in multi-layer networks is proposed, which simultaneously learns the deep representation and discriminative features. Specifically, DRDF learns the deep representation with deep nonnegative matrix factorization, where the high-order topology of the multi-layer network is gradually and precisely characterized. Moreover, it addresses the specificity of modules with discriminative feature learning, where the intra-class compactness and inter-class separation of pseudo-labels of clusters are explored as self-supervised information, thereby providing a more accurate method to explicitly model the specificity of the multi-layer network. Finally, DRDF balances the connectivity and specificity of layer-specific modules with joint learning, where the overall objective of the graph clustering algorithm and optimization rules are derived. The experiments on ten multi-layer networks showed that DRDF not only outperforms eight baselines on graph clustering but also enhances the robustness of algorithms.

EGST: Enhanced Geometric Structure Transformer for Point Cloud Registration.

We explore the effect of geometric structure descriptors on extracting reliable correspondences and obtaining accurate registration for point cloud registration. The point cloud registration task involves the estimation of rigid transformation motion in unorganized point cloud, hence it is crucial to capture the contextual features of the geometric structure in point cloud. Recent coordinates-only methods ignore numerous geometric information in the point cloud which weaken ability to express the global context. We propose Enhanced Geometric Structure Transformer to learn enhanced contextual features of the geometric structure in point cloud and model the structure consistency between point clouds for extracting reliable correspondences, which encodes three explicit enhanced geometric structures and provides significant cues for point cloud registration. More importantly, we report empirical results that Enhanced Geometric Structure Transformer can learn meaningful geometric structure features using none of the following: (i) explicit positional embeddings, (ii) additional feature exchange module such as cross-attention, which can simplify network structure compared with plain Transformer. Extensive experiments on the synthetic dataset and real-world datasets illustrate that our method can achieve competitive results.

Self-Supervised Monocular Depth Estimation With Self-Perceptual Anomaly Handling.

It is attractive to extract plausible 3-D information from a single 2-D image, and self-supervised learning has shown impressive potential in this field. However, when only monocular videos are available as training data, moving objects at similar speeds to the camera can disturb the reprojection process during training. Existing methods filter out some moving pixels by comparing pixelwise photometric error, but the illumination inconsistency between frames leads to incomplete filtering. In addition, existing methods calculate photometric error within local windows, which leads to the fact that even if an anomalous pixel is masked out, it can still implicitly disturb the reprojection process, as long as it is in the local neighborhood of a nonanomalous pixel. Moreover, the ill-posed nature of monocular depth estimation makes the same scene correspond to multiple plausible depth maps, which damages the robustness of the model. In order to alleviate the above problems, we propose: 1) a self-reprojection mask to further filter out moving objects while avoiding illumination inconsistency; 2) a self-statistical mask method to prevent the filtered anomalous pixels from implicitly disturbing the reprojection; and 3) a self-distillation augmentation consistency loss to reduce the impact of ill-posed nature of monocular depth estimation. Our method shows superior performance on the KITTI dataset, especially when evaluating only the depth of potential moving objects.

A Collaborative Multimodal Learning-Based Framework for COVID-19 Diagnosis.

The pandemic of coronavirus disease 2019 (COVID-19) has led to a global public health crisis, which caused millions of deaths and billions of infections, greatly increasing the pressure on medical resources. With the continuous emergence of viral mutations, developing automated tools for COVID-19 diagnosis is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. However, medical images in a single site are usually of a limited amount or weakly labeled, while integrating data scattered around different institutions to build effective models is not allowed due to data policy restrictions. In this article, we propose a novel privacy-preserving cross-site framework for COVID-19 diagnosis with multimodal data, seeking to effectively leverage heterogeneous data from multiple parties while preserving patients' privacy. Specifically, a Siamese branched network is introduced as the backbone to capture inherent relationships across heterogeneous samples. The redesigned network is capable of handling semisupervised inputs in multimodalities and conducting task-specific training, in order to improve the model performance of various scenarios. The framework achieves significant improvement compared with state-of-the-art methods, as we demonstrate through extensive simulations on real-world datasets.

Device-Performance-Driven Heterogeneous Multiparty Learning for Arbitrary Images.

Multiparty learning (MPL) is an emerging framework for privacy-preserving collaborative learning. It enables individual devices to build a knowledge-shared model and remaining sensitive data locally. However, with the continuous increase of users, the heterogeneity gap between data and equipment becomes wider, which leads to the problem of model heterogeneous. In this article, we concentrate on two practical issues: data heterogeneous problem and model heterogeneous problem, and propose a novel personal MPL method named device-performance-driven heterogeneous MPL (HMPL). First, facing the data heterogeneous problem, we focus on the problem of various devices holding arbitrary data sizes. We introduce a heterogeneous feature-map integration method to adaptively unify the various feature maps. Meanwhile, to handle the model heterogeneous problem, as it is essential to customize models for adapting to the various computing performances, we propose a layer-wise model generation and aggregation strategy. The method can generate customized models based on the device's performance. In the aggregation process, the shared model parameters are updated through the rules that the network layers with the same semantics are aggregated with each other. Extensive experiments are conducted on four popular datasets, and the result demonstrates that our proposed framework outperforms the state of the art (SOTA).

RORNet: Partial-to-Partial Registration Network With Reliable Overlapping Representations.

Three-dimensional point cloud registration is an important field in computer vision. Recently, due to the increasingly complex scenes and incomplete observations, many partial-overlap registration methods based on overlap estimation have been proposed. These methods heavily rely on the extracted overlapping regions with their performances greatly degraded when the overlapping region extraction underperforms. To solve this problem, we propose a partial-to-partial registration network (RORNet) to find reliable overlapping representations from the partially overlapping point clouds and use these representations for registration. The idea is to select a small number of key points called reliable overlapping representations from the estimated overlapping points, reducing the side effect of overlap estimation errors on registration. Although it may filter out some inliers, the inclusion of outliers has a much bigger influence than the omission of inliers on the registration task. The RORNet is composed of overlapping points' estimation module and representations' generation module. Different from the previous methods of direct registration after extraction of overlapping areas, RORNet adds the step of extracting reliable representations before registration, where the proposed similarity matrix downsampling method is used to filter out the points with low similarity and retain reliable representations, and thus reduce the side effects of overlap estimation errors on the registration. Besides, compared with previous similarity-based and score-based overlap estimation methods, we use the dual-branch structure to combine the benefits of both, which is less sensitive to noise. We perform overlap estimation experiments and registration experiments on the ModelNet40 dataset, outdoor large scene dataset KITTI, and natural data Stanford Bunny dataset. The experimental results demonstrate that our method is superior to other partial registration methods. Our code is available at https://github.com/superYuezhang/RORNet.

Heterogeneous Multi-Party Learning With Data-Driven Network Sampling.

Multi-party learning provides an effective approach for training a machine learning model, e.g., deep neural networks (DNNs), over decentralized data by leveraging multiple decentralized computing devices, subjected to legal and practical constraints. Different parties, so-called local participants, usually provide heterogenous data in a decentralized mode, leading to non-IID data distributions across different local participants which pose a notorious challenge for multi-party learning. To address this challenge, we propose a novel heterogeneous differentiable sampling (HDS) framework. Inspired by the dropout strategy in DNNs, a data-driven network sampling strategy is devised in the HDS framework, with differentiable sampling rates which allow each local participant to extract from a common global model the optimal local model that best adapts to its own data properties so that the size of the local model can be significantly reduced to enable more efficient inference. Meanwhile, co-adaptation of the global model via learning such local models allows for achieving better learning performance under non-IID data distributions and speeds up the convergence of the global model. Experiments have demonstrated the superiority of the proposed method over several popular multi-party learning techniques in the multi-party settings with non-IID data distributions.

Semisupervised Change Detection Based on Bihierarchical Feature Aggregation and Extraction Network.

With the rapid development of remote sensing (RS) technology, high-resolution RS image change detection (CD) has been widely used in many applications. Pixel-based CD techniques are maneuverable and widely used, but vulnerable to noise interference. Object-based CD techniques can effectively utilize the abundant spectrum, texture, shape, and spatial information but easy-to-ignore details of RS images. How to combine the advantages of pixel-based methods and object-based methods remains a challenging problem. Besides, although supervised methods have the capability to learn from data, the true labels representing changed information of RS images are often hard to obtain. To address these issues, this article proposes a novel semisupervised CD framework for high-resolution RS images, which employs small amounts of true labeled data and a lot of unlabeled data to train the CD network. A bihierarchical feature aggregation and extraction network (BFAEN) is designed to achieve the pixelwise together with objectwise feature concatenation feature representation for the comprehensive utilization of the two-level features. In order to alleviate the coarseness and insufficiency of labeled samples, a confident learning algorithm is used to eliminate noisy labels and a novel loss function is designed for training the model using true-and pseudo-labels in a semisupervised fashion. Experimental results on real datasets demonstrate the effectiveness and superiority of the proposed method.

Feature Weighted Non-Negative Matrix Factorization.

Non-negative matrix factorization (NMF) is one of the most popular techniques for data representation and clustering and has been widely used in machine learning and data analysis. NMF concentrates the features of each sample into a vector and approximates it by the linear combination of basis vectors, such that the low-dimensional representations are achieved. However, in real-world applications, the features usually have different importance. To exploit the discriminative features, some methods project the samples into the subspace with a transformation matrix, which disturbs the original feature attributes and neglects the diversity of samples. To alleviate the above problems, we propose the feature weighted NMF (FNMF) in this article. The salient properties of FNMF can be summarized as three-fold: 1) it learns the weights of features adaptively according to their importance; 2) it utilizes multiple feature weighting components to preserve the diversity; and 3) it can be solved efficiently with the suggested optimization algorithm. The performance on synthetic and real-world datasets demonstrates that the proposed method obtains the state-of-the-art performance.

Modeling Cardinality in Image Hashing.

Cardinality constraint, namely, constraining the number of nonzero outputs of models, has been widely used in structural learning. It can be used for modeling the dependencies between multidimensional labels. In hashing, the final outputs are also binary codes, which are similar to multidimensional labels. It has been validated that estimating how many 1's in a multidimensional label vector is easier than directly predicting which elements are 1 and estimating cardinality as a prior step will improve the classification performance. Hence, in this article, we incorporate cardinality constraint into the unsupervised image hashing problem. The proposed model is divided into two steps: 1) estimating the cardinalities of hashing codes and 2) then estimating which bits are 1. Unlike multidimensional labels that are known and fixed in the training phase, the hashing codes are generally learned through an iterative method and, therefore, their cardinalities are unknown and not fixed during the learning procedure. We use a neural network as a cardinality predictor and its parameters are jointly learned with the hashing code generator, which is an autoencoder in our model. The experiments demonstrate the efficiency of our proposed method.

Clustering of Multilayer Networks Using Joint Learning Algorithm With Orthogonality and Specificity of Features.

Complex systems in nature and society consist of various types of interactions, where each type of interaction belongs to a layer, resulting in the so-called multilayer networks. Identifying specific modules for each layer is of great significance for revealing the structure-function relations in multilayer networks. However, the available approaches are criticized undesirable because they fail to explicitly the specificity of modules, and balance the specificity and connectivity of modules. To overcome these drawbacks, we propose an accurate and flexible algorithm by joint learning matrix factorization and sparse representation (jMFSR) for specific modules in multilayer networks, where matrix factorization extracts features of vertices and sparse representation discovers specific modules. To exploit the discriminative latent features of vertices in multilayer networks, jMFSR incorporates linear discriminant analysis (LDA) into non-negative matrix factorization (NMF) to learn features of vertices that distinguish the categories. To explicitly measure the specificity of features, jMFSR decomposes features of vertices into common and specific parts, thereby enhancing the quality of features. Then, jMFSR jointly learns feature extraction, common-specific feature factorization, and clustering of multilayer networks. The experiments on 11 datasets indicate that jMFSR significantly outperforms state-of-the-art baselines in terms of various measurements.

AudioVisual Video Summarization.

Audio and vision are two main modalities in video data. Multimodal learning, especially for audiovisual learning, has drawn considerable attention recently, which can boost the performance of various computer vision tasks. However, in video summarization, most existing approaches just exploit the visual information while neglecting the audio information. In this brief, we argue that the audio modality can assist vision modality to better understand the video content and structure and further benefit the summarization process. Motivated by this, we propose to jointly exploit the audio and visual information for the video summarization task and develop an audiovisual recurrent network (AVRN) to achieve this. Specifically, the proposed AVRN can be separated into three parts: 1) the two-stream long-short term memory (LSTM) is used to encode the audio and visual feature sequentially by capturing their temporal dependency; 2) the audiovisual fusion LSTM is used to fuse the two modalities by exploring the latent consistency between them; and 3) the self-attention video encoder is adopted to capture the global dependency in the video. Finally, the fused audiovisual information and the integrated temporal and global dependencies are jointly used to predict the video summary. Practically, the experimental results on the two benchmarks, i.e., SumMe and TVsum, have demonstrated the effectiveness of each part and the superiority of AVRN compared with those approaches just exploiting visual information for video summarization.

Joint Learning of Feature Extraction and Clustering for Large-Scale Temporal Networks.

Temporal networks are ubiquitous in nature and society, and tracking the dynamics of networks is fundamental for investigating the mechanisms of systems. Dynamic communities in temporal networks simultaneously reflect the topology of the current snapshot (clustering accuracy) and historical ones (clustering drift). Current algorithms are criticized for their inability to characterize the dynamics of networks at the vertex level, independence of feature extraction and clustering, and high time complexity. In this study, we solve these problems by proposing a novel joint learning model for dynamic community detection in temporal networks (also known as jLMDC) via joining feature extraction and clustering. This model is formulated as a constrained optimization problem. Vertices are classified into dynamic and static groups by exploring the topological structure of temporal networks to fully exploit their dynamics at each time step. Then, jLMDC updates the features of dynamic vertices by preserving features of static ones during optimization. The advantage of jLMDC is that features are extracted under the guidance of clustering, promoting performance, and saving the running time of the algorithm. Finally, we extend jLMDC to detect the overlapping dynamic community in temporal networks. The experimental results on 11 temporal networks demonstrate that jLMDC improves accuracy up to 8.23% and saves 24.89% of running time on average compared to state-of-the-art methods.

Solving Expensive Multimodal Optimization Problem by a Decomposition Differential Evolution Algorithm.

An expensive multimodal optimization problem (EMMOP) is that the computation of the objective function is time consuming and it has multiple global optima. This article proposes a decomposition differential evolution (DE) based on the radial basis function (RBF) for EMMOPs, called D/REM. It mainly consists of two phases: the promising subregions detection (PSD) and the local search phase (LSP). In PSD, a population update strategy is designed and the mean-shift clustering is employed to predict the promising subregions of EMMOP. In LSP, a local RBF surrogate model is constructed for each promising subregion and each local RBF surrogate model tracks a global optimum of EMMOP. In this way, an EMMOP is decomposed into many expensive global optimization subproblems. To handle these subproblems, a popular DE variant, JADE, acts as the search engine to deal with these subproblems. A large number of numerical experiments unambiguously validate that D/REM can solve EMMOPs effectively and efficiently.

Self-Paced Co-Training of Graph Neural Networks for Semi-Supervised Node Classification.

Graph neural networks (GNNs) have demonstrated great success in many graph data-based applications. The impressive behavior of GNNs typically relies on the availability of a sufficient amount of labeled data for model training. However, in practice, obtaining a large number of annotations is prohibitively labor-intensive and even impossible. Co-training is a popular semi-supervised learning (SSL) paradigm, which trains multiple models based on a common training set while augmenting the limited amount of labeled data used for training each model via the pseudolabeled data generated from the prediction results of other models. Most of the existing co-training works do not control the quality of pseudolabeled data when using them. Therefore, the inaccurate pseudolabels generated by immature models in the early stage of the training process are likely to cause noticeable errors when they are used for augmenting the training data for other models. To address this issue, we propose a self-paced co-training for the GNN (SPC-GNN) framework for semi-supervised node classification. This framework trains multiple GNNs with the same or different structures on different representations of the same training data. Each GNN carries out SSL by using both the originally available labeled data and the augmented pseudolabeled data generated from other GNNs. To control the quality of pseudolabels, a self-paced label augmentation strategy is designed to make the pseudolabels generated at a higher confidence level to be utilized earlier during training such that the negative impact of inaccurate pseudolabels on training data augmentation, and accordingly, the subsequent training process can be mitigated. Finally, each of the trained GNN is evaluated on a validation set, and the best-performing one is chosen as the output. To improve the training effectiveness of the framework, we devise a pretraining followed by a two-step optimization scheme to train GNNs. Experimental results on the node classification task demonstrate that the proposed framework achieves significant improvement over the state-of-the-art SSL methods.

Multiparty Dual Learning.

The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this article, we propose a multiparty dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge-sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multiparty learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than nondistributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multiparty learning methods, as we demonstrated through simulations on real-world datasets.

Semisupervised Graph Neural Networks for Graph Classification.

Graph classification aims to predict the label associated with a graph and is an important graph analytic task with widespread applications. Recently, graph neural networks (GNNs) have achieved state-of-the-art results on purely supervised graph classification by virtue of the powerful representation ability of neural networks. However, almost all of them ignore the fact that graph classification usually lacks reasonably sufficient labeled data in practical scenarios due to the inherent labeling difficulty caused by the high complexity of graph data. The existing semisupervised GNNs typically focus on the task of node classification and are incapable to deal with graph classification. To tackle the challenging but practically useful scenario, we propose a novel and general semisupervised GNN framework for graph classification, which takes full advantage of a slight amount of labeled graphs and abundant unlabeled graph data. In our framework, we train two GNNs as complementary views for collaboratively learning high-quality classifiers using both labeled and unlabeled graphs. To further exploit the view itself, we constantly select pseudo-labeled graph examples with high confidence from its own view for enlarging the labeled graph dataset and enhancing predictions on graphs. Furthermore, the proposed framework is investigated on two specific implementation regimes with a few labeled graphs and the extremely few labeled graphs, respectively. Extensive experimental results demonstrate the effectiveness of our proposed semisupervised GNN framework for graph classification on several benchmark datasets.