Although unsupervised multiplex graph representation learning (UMGRL) has been a hot research topic, existing UMGRL methods still has limitations to be addressed. For example, previous works either preserve structural information by ignoring the impact of heterophily in the graph structure or only focus on node-level consistency by ignoring class-level consistency. To address these issues, in this paper, we propose a new UMGRL method to explore both homophily and consistency in the multiplex graph. Specifically, we propose to restructure the multi-order relationships of every graph between every node and its multi-order neighbors to improve the homophily and reduce the impact of the heterophily in the graph structure. We also design a contrastive loss based on a self-expression matrix of the node representation to achieve node-level and class-level consistency. Furthermore, we theoretically prove our method to achieve class-level consistency. Extensive experimental results on real datasets verify the effectiveness of the proposed method with respect to node classification tasks, compared to SOTA methods.

Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model. Finally, we design a label improvement module to improve the label quality. Extensive experimental results on real datasets show that our method achieves the best results compared to state-of-the-art methods.

Chinese poetry, renowned for its elegance and simplicity, is a hallmark of Chinese culture. While neural networks have made significant advancements in generating poetry, balancing diversity with adherence to rigid structural formats remains a challenge. Research indicates that factors such as themes, emotions (e.g., happiness, sadness), and sentiments (e.g., positive, negative) play a crucial role in poetic creation, influencing both the diversity and quality of the generated content. In this paper, we propose MixSong, an autoregressive language model based on the Transformer architecture, designed to incorporate a wide range of conditional factors. MixSong utilizes adversarial training to integrate these factors, enabling the model to implicitly learn distributional information in the latent space. Additionally, we introduce several uniquely customized symbol sets, including paragraph identifiers, position identifiers, rhyme identifiers, tune identifiers, and conditional distinctive identifiers. These symbols help MixSong effectively capture and enforce the constraints necessary for generating high-quality poetry. Extensive experimental results demonstrate that MixSong significantly outperforms existing models in both automatic metrics and human evaluations, achieving notable improvements in both diversity and quality of the generated poetry.

Current research for node classification focuses on dealing with either graph noise or label noise, but few studies consider both of them. In this paper, we propose a new robust node classification method to simultaneously deal with graph noise and label noise. To do this, we design a graph contrastive loss to conduct local graph learning and employ self-attention to conduct global graph learning. They enable us to improve the expressiveness of node representation by using comprehensive information among nodes. We also utilize pseudo graphs and pseudo labels to deal with graph noise and label noise, respectively. Furthermore, We numerically validate the superiority of our method in terms of robust node classification compared with all comparison methods.

Graph convolutional network (GCN) outputs powerful representation by considering the structure information of the data to conduct representation learning, but its robustness is sensitive to the quality of both the feature matrix and the initial graph. In this article, we propose a novel multigraph fusion method to produce a high-quality graph and a low-dimensional space of original high-dimensional data for the GCN model. Specifically, the proposed method first extracts the common information and the complementary information among multiple local graphs to obtain a unified local graph, which is then fused with the global graph of the data to obtain the initial graph for the GCN model. As a result, the proposed method conducts the graph fusion process twice to simultaneously learn the low-dimensional space and the intrinsic graph structure of the data in a unified framework. Experimental results on real datasets demonstrated that our method outperformed the comparison methods in terms of classification tasks.

Graph Neural Networks (GNN) are an effective technique for node classification, but their performance is easily affected by the quality of the primitive graph and the limited receptive field of message-passing. In this paper, we propose a new self-attention method, namely Chain of Propagation Prompting (CPP), to address the above issues as well as reduce dependence on label information when employing self-attention for node classification. To do this, we apply the self-attention framework to reduce the impact of a low-quality graph and to obtain a maximal receptive field for the message-passing. We also design a simple pattern of message-passing as the prompt to make self-attention capture complex patterns and reduce the dependence on label information. Comprehensive experimental results on real graph datasets demonstrate that CPP outperforms all relevant comparison methods.

The classification service over a stream of data is becoming an important offering for cloud providers, but users may encounter obstacles in providing sensitive data due to privacy concerns. While Trusted Execution Environments (TEEs) are promising solutions for protecting private data, they remain vulnerable to side-channel attacks induced by data-dependent access patterns. We propose a Privacy-preserving Data Stream Training and Inference scheme, called EnclaveTree, that provides confidentiality for user's data and the target models against a compromised cloud service provider. We design a matrix-based training and inference procedure to train the Hoeffding Tree (HT) model and perform inference with the trained model inside the trusted area of TEEs, which provably prevent the exploitation of access-pattern-based attacks. The performance evaluation shows that EnclaveTree is practical for processing the data streams with small or medium number of features. When there are less than 63 binary features,EnclaveTree is up to ~10x and ~9 faster than naïve oblivious solution on training and inference, respectively.

Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has performed the desired reasoning to reach the correct answer. Most existing multi-hop QA methods fail to answer a large fraction of sub-questions, even if their parent questions are answered correctly. In this paper, we propose the Prompt-based Conservation Learning (PCL) framework for multi-hop QA, which acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop QA tasks, mitigating forgetting. Specifically, we first train a model on existing single-hop QA tasks, and then freeze this model and expand it by allocating additional sub-networks for the multi-hop QA task. Moreover, to condition pre-trained language models to stimulate the kind of reasoning required for specific multi-hop questions, we learn soft prompts for the novel sub-networks to perform type-specific reasoning. Experimental results on the HotpotQA benchmark show that PCL is competitive for multi-hop QA and retains good performance on the corresponding single-hop sub-questions, demonstrating the efficacy of PCL in mitigating knowledge loss by forgetting.

Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these models arrive at an answer. In this paper, we propose a Question Decomposition method based on Abstract Meaning Representation (QDAMR) for multi-hop QA, which achieves interpretable reasoning by decomposing a multi-hop question into simpler subquestions and answering them in order. Since annotating the decomposition is expensive, we first delegate the complexity of understanding the multi-hop question to an AMR parser. We then achieve decomposition of a multi-hop question via segmentation of the corresponding AMR graph based on the required reasoning type. Finally, we generate sub-questions using an AMR-to-Text generation model and answer them with an off-the-shelf QA model. Experimental results on HotpotQA demonstrate that our approach is competitive for interpretable reasoning and that the sub-questions generated by QDAMR are well-formed, outperforming existing question-decomposition-based multihop QA approaches.

Unsupervised spectral feature selection (USFS) methods could output interpretable and discriminative results by embedding a Laplacian regularizer in the framework of sparse feature selection to keep the local similarity of the training samples. To do this, USFS methods usually construct the Laplacian matrix using either a general-graph or a hyper-graph on the original data. Usually, a general-graph could measure the relationship between two samples while a hyper-graph could measure the relationship among no less than two samples. Obviously, the general-graph is a special case of the hyper-graph and the hyper-graph may capture more complex structure of samples than the general graph. However, in previous USFS methods, the construction of the Laplacian matrix is separated from the process of feature selection. Moreover, the original data usually contain noise. Each of them makes difficult to output reliable feature selection models. In this paper, we propose a novel feature selection method by dynamically constructing a hyper-graph based Laplacian matrix in the framework of sparse feature selection. Experimental results on real datasets showed that our proposed method outperformed the state-of-the-art methods in terms of both clustering and segmentation tasks.

Abstract Spectral clustering is widely applied in real applications, as it utilizes a graph matrix to consider the similarity relationship of subjects. The quality of graph structure is usually important to the robustness of the clustering task. However, existing spectral clustering methods consider either the local structure or the global structure, which can not provide comprehensive information for clustering tasks. Moreover, previous clustering methods only consider the simple similarity relationship, which may not output the optimal clustering performance. To solve these problems, we propose a novel clustering method considering both the local structure and the global structure for conducting nonlinear clustering. Specifically, our proposed method simultaneously considers (i) preserving the local structure and the global structure of subjects to provide comprehensive information for clustering tasks, (ii) exploring the nonlinear similarity relationship to capture the complex and inherent correlation of subjects and (iii) embedding dimensionality reduction techniques and a low-rank constraint in the framework of adaptive graph learning to reduce clustering biases. These constraints are considered in a unified optimization framework to result in one-step clustering. Experimental results on real data sets demonstrate that our method achieved competitive clustering performance in comparison with state-of-the-art clustering methods.

The functional connectomic profile is one of the non-invasive imaging biomarkers in the computer-assisted diagnostic system for many neuro-diseases. However, the diagnostic power of functional connectivity is challenged by mixed frequency-specific neuronal oscillations in the brain, which makes the single Functional Connectivity Network (FCN) often underpowered to capture the disease-related functional patterns. To address this challenge, we propose a novel functional connectivity analysis framework to conduct joint feature learning and personalized disease diagnosis, in a semi-supervised manner, aiming at focusing on putative multi-band functional connectivity biomarkers from functional neuroimaging data. Specifically, we first decompose the Blood Oxygenation Level Dependent (BOLD) signals into multiple frequency bands by the discrete wavelet transform, and then cast the alignment of all fully-connected FCNs derived from multiple frequency bands into a parameter-free multi-band fusion model. The proposed fusion model fuses all fully-connected FCNs to obtain a sparsely-connected FCN (sparse FCN for short) for each individual subject, as well as lets each sparse FCN be close to its neighbored sparse FCNs and be far away from its furthest sparse FCNs. Furthermore, we employ the$\ell _{{1}}$-SVM to conduct joint brain region selection and disease diagnosis. Finally, we evaluate the effectiveness of our proposed framework on various neuro-diseases,i.e.,Fronto-Temporal Dementia (FTD), Obsessive-Compulsive Disorder (OCD), and Alzheimer’s Disease (AD), and the experimental results demonstrate that our framework shows more reasonable results, compared to state-of-the-art methods, in terms of classification performance and the selected brain regions. The source code can be visited by the urlhttps://github.com/reynard-hu/mbbna.

Unsupervised feature selection (UFS) is a popular technique of reducing the dimensions of high-dimensional data. Previous UFS methods were often designed with the assumption that the whole information in the data set is observed. However, incomplete data sets that contain unobserved information can be often found in real applications, especially in industry. Thus, these existing UFS methods have a limitation on conducting feature selection on incomplete data. On the other hand, most existing UFS methods did not consider the sample importance for feature selection, i.e., different samples have various importance. As a result, the constructed UFS models easily suffer from the influence of outliers. This article investigates a new UFS method for conducting UFS on incomplete data sets to investigate the abovementioned issues. Specifically, the proposed method deals with unobserved information by using an indicator matrix to filter it out the process of feature selection and reduces the influence of outliers by employing the half-quadratic minimization technique to automatically assigning outliers with small or even zero weights and important samples with large weights. This article further designs an alternative optimization strategy to optimize the proposed objective function as well as theoretically and experimentally prove the convergence of the proposed optimization strategy. Experimental results on both real and synthetic incomplete data sets verified the effectiveness of the proposed method compared with previous methods, in terms of clustering performance on the low-dimensional space of the high-dimensional data.

Brain functional connectivity analysis on fMRI data could improve the understanding of human brain function. However, due to the influence of the inter-subject variability and the heterogeneity across subjects, previous methods of functional connectivity analysis are often insufficient in capturing disease-related representation so that decreasing disease diagnosis performance. In this paper, we first propose a new multi-graph fusion framework to fine-tune the original representation derived from Pearson correlation analysis, and then employ L1-SVM on fine-tuned representations to conduct joint brain region selection and disease diagnosis for avoiding the issue of the curse of dimensionality on high-dimensional data. The multi-graph fusion framework automatically learns the connectivity number for every node (i.e., brain region) and integrates all subjects in a unified framework to output homogenous and discriminative representations of all subjects. Experimental results on two real data sets, i.e., fronto-temporal dementia (FTD) and obsessive-compulsive disorder (OCD), verified the effectiveness of our proposed framework, compared to state-of-the-art methods.

Summary The multimedia contents shared on social network reveal public sentimental attitudes toward specific events. Therefore, it is necessary to conduct sentiment analysis automatically on abundant multimedia data posted by the public for real‐world applications. However, approaches to single‐modal sentiment analysis neglect the internal connections between textual and visual contents, and current multimodal methods fail to exploit the multilevel semantic relations of heterogeneous features. In this article, the various syncretic co‐attention network is proposed to excavate the intricate multilevel corresponding relations between multimodal data, and combine the unique information of each modality for integrated complementary sentiment classification. Specifically, a multilevel co‐attention module is constructed to explore localized correspondences between each image region and each text word, and holistic correspondences between global visual information and context‐based textual semantics. Then, all the single‐modal features can be fused from different levels, respectively. Except for fused multimodal features, our proposed VSCN also considers unique information of each modality simultaneously and integrates them into an end‐to‐end framework for sentiment analysis. The superior results of experiments on three constructed real‐world datasets and a benchmark dataset of Visual Sentiment Ontology (VSO) prove the effectiveness of our proposed VSCN. Especially qualitative analyses are given for deep explaining of our method.

Since the data in each view may contain distinct information different from other views as well as has common information for all views in multi-view learning, many multi-view clustering methods have been designed to use these information (including the distinct information for each view and the common information for all views) to improve the clustering performance. However, previous multi-view clustering methods cannot effectively detect these information so that difficultly outputting reliable clustering models. In this article, we propose a fuzzy, sparse, and robust multi-view clustering method to consider all kinds of relations among the data (such as view importance, view stability, and view diversity), which can effectively extract both distinct information and common information as well as balance these two kinds of information. Moreover, we devise an alternating optimization algorithm to solve the resulting objective function as well as prove that our proposed algorithm achieves fast convergence. It is noteworthy that existing multi-view clustering methods only consider a part of the relations, and thus are a special case of our proposed framework. Experimental results on synthetic datasets and real datasets show that our proposed method outperforms the state-of-the-art clustering methods in terms of evaluation metrics of clustering such as clustering accuracy, normalized mutual information, purity, and adjusted rand index.

Abstract A scene graph provides a powerful intermediate knowledge structure for various visual tasks, including semantic image retrieval, image captioning, and visual question answering. In this paper, the task of predicting a scene graph for an image is formulated as two connected problems, ie, recognizing the relationship triplets, structured as <subject‐predicate‐object>, and constructing the scene graph from the recognized relationship triplets. For relationship triplet recognition, we develop a novel hierarchical recurrent neural network with visual attention mechanism. This model is composed of two attention‐based recurrent neural networks in a hierarchical organization. The first network generates a topic vector for each relationship triplet, whereas the second network predicts each word in that relationship triplet given the topic vector. This approach successfully captures the compositional structure and contextual dependency of an image and the relationship triplets describing its scene. For scene graph construction, an entity localization approach to determine the graph structure is presented with the assistance of available attention information. Then, the procedures for automatically converting the generated relationship triplets into a scene graph are clarified through an algorithm. Extensive experimental results on two widely used data sets verify the feasibility of the proposed approach.

Feature selection is an indispensable preprocessing procedure for high-dimensional data analysis,but previous feature selection methods usually ignore sample diversity (i.e., every sample has individual contribution for the model construction) andhave limited ability to deal with incomplete datasets where a part of training samples have unobserved data. To address these issues, in this paper, we firstly propose a robust feature selectionframework to relieve the influence of outliers, andthen introduce an indicator matrix to avoid unobserved data to take participation in numerical computation of feature selection so that both our proposed feature selection framework and exiting feature selection frameworks are available to conductfeature selection on incomplete data sets. We further propose a new optimization algorithm to optimize the resulting objective function as well asprove our algorithm to converge fast. Experimental results on both real and artificial incompletedata sets demonstrated that our proposed methodoutperformed the feature selection methods undercomparison in terms of clustering performance.

Although multi-view clustering is capable to usemore information than single view clustering, existing multi-view clustering methods still have issues to be addressed, such as initialization sensitivity, the specification of the number of clusters,and the influence of outliers. In this paper, we propose a robust multi-view clustering method to address these issues. Specifically, we first propose amulti-view based sum-of-square error estimation tomake the initialization easy and simple as well asuse a sum-of-norm regularization to automaticallylearn the number of clusters according to data distribution. We further employ robust estimators constructed by the half-quadratic theory to avoid theinfluence of outliers for conducting robust estimations of both sum-of-square error and the numberof clusters. Experimental results on both syntheticand real datasets demonstrate that our method outperforms the state-of-the-art methods.

This paper proposes a new unsupervised spectral feature selection method to preserve both the local and global structure of the features as well as the samples. Specifically, our method uses the self-expressiveness of the features to represent each feature by other features for preserving the local structure of features, and a low-rank constraint on the weight matrix to preserve the global structure among samples as well as features. Our method also proposes to learn the graph matrix measuring the similarity of samples for preserving the local structure among samples. Furthermore, we propose a new optimization algorithm to the resulting objective function, which iteratively updates the graph matrix and the intrinsic space so that collaboratively improving each of them. Experimental analysis on 12 benchmark datasets showed that the proposed method outperformed the state-of-the-art feature selection methods in terms of classification performance.

This paper proposes a one-step spectral clustering method by learning an intrinsic affinity matrix (i.e., the clustering result) from the low-dimensional space (i.e., intrinsic subspace) of original data. Specifically, the intrinsic affinitymatrix is learnt by: 1) the alignment of the initial affinity matrix learnt from original data; 2) the adjustment of the transformation matrix, which transfers the original feature space into its intrinsic subspace by simultaneously conducting feature selection and subspace learning; and 3) the clustering result constraint, i.e., the graph constructed by the intrinsic affinity matrix has exact c connected components where c is the number of clusters. In this way, two affinity matrices and a transformation matrix are iteratively updated until achieving their individual optimum, so that these two affinity matrices are consistent and the intrinsic subspace is learnt via the transformation matrix. Experimental results on both synthetic and benchmark datasets verified that our proposed method outputted more effective clustering result than the previous clustering methods.

Current unsupervised feature selection (UFS) methods learn the similarity matrix by using a simple graph which is learnt from the original data as well as is independent from the process of feature selection, and thus unable to efficiently remove the redundant/irrelevant features. To address these issues, we propose a new UFS method to jointly learn the similarity matrix and conduct both subspace learning (via learning a dynamic hypergraph) and feature selection (via a sparsity constraint). As a result, we reduce the feature dimensions using different methods (i.e., subspace learning and feature selection) from different feature spaces, and thus makes our method select the informative features effectively and robustly. We tested our method using benchmark datasets to conduct the clustering tasks using the selected features, and the experimental results show that our proposed method outperforms all the comparison methods.

In recent years, web technologies as well as XML have gained broad application throughout the industry. Web services have become increasingly important for network application solutions since the business processes are no longer constrained by company-related boundaries by the use of web services. In order to avoid the considerable mass of repeated time consuming hand coding at low-level, a SQL-based Web Services Automatic Generating Strategy is put forward in this paper which enables users to generate personalized web services automatically by SQL statements with additional custom tags defined in the strategy. By adopting this strategy, enterprises can shorten development cycle and reduce the cost of both financial and human resources. Finally, an architecture is implemented where dynamic web services can be automatically created. The experiment results prove that the SQL-based web services automatic generating strategy proposed is simple and extendable to build and deploy web services at run-time.