As the application of knowledge graphs becomes increasingly widespread, the issue of knowledge graph incompleteness has garnered significant attention. As a classical type of non-euclidean spatial data, knowledge graphs possess various complex structural types. However, most current knowledge graph completion models are developed within a single space, which makes it challenging to capture the inherent knowledge information embedded in the entire knowledge graph. This limitation hinders the representation learning capability of the models. To address this issue, this paper focuses on how to better extend the representation learning from a single space to Riemannian manifolds, which are capable of representing more complex structures. We propose a new knowledge graph completion model called MRME-KGC, based on multi-view Riemannian Manifolds fusion to achieve this. Specifically, MRME-KGC simultaneously considers the fusion of four views: two hyperbolic Riemannian spaces with negative curvature, a Euclidean Riemannian space with zero curvature, and a spherical Riemannian space with positive curvature to enhance knowledge graph modeling. Additionally, this paper proposes a contrastive learning method for Riemannian spaces to mitigate the noise and representation issues arising from Multi-view Riemannian Manifolds Fusion. This paper presents extensive experiments on MRME-KGC across multiple datasets. The results consistently demonstrate that MRME-KGC significantly outperforms current state-of-the-art models, achieving highly competitive performance even with low-dimensional embeddings.

Noisy-label data inevitably gives rise to confusion in various perception applications. In this work, we revisit the theory of support vector machines (SVM) which mines support vectors to build the maximum-margin hyperplane for robust classification, and propose a robust-to-noise deep learning framework, SV-Learner, including the Support Vector Contrastive Learning (SVCL) and Support Vector-based Noise Screening (SVNS). The SV-Learner mines support vectors to solve the learning problem with noisy labels (LNL) reliably. Support Vector Contrastive Learning (SVCL) adopts support vectors as positive and negative samples, driving robust contrastive learning to enlarge the feature distribution margin for learning convergent feature distributions. Support Vector-based Noise Screening (SVNS) uses support vectors with valid labels to assist in screening noisy ones from confusable samples for reliable clean-noisy sample screening. Finally, Semi-Supervised classification is performed to realize the recognition of noisy samples. Extensive experiments are evaluated on CIFAR-10, CIFAR-100, Clothing1M, and Webvision datasets, and results demonstrate the effectiveness of our proposed approach. The source code is availablehttps://github.com/yanliji/SV-Learner.

Machine Unlearning, a pivotal field addressing data privacy in machine learning, necessitates efficient methods for the removal of private or irrelevant data. In this context, significant challenges arise, particularly in maintaining privacy and ensuring model efficiency when managing outdated, private, and irrelevant data. Such data not only compromises model accuracy but also burdens computational efficiency in both learning and unlearning processes. To mitigate these challenges, we introduce a novel framework: Attention-based Machine Unlearning using Federated Reinforcement Learning (FRAMU). This framework incorporates adaptive learning mechanisms, privacy preservation techniques, and optimization strategies, making it a well-rounded solution for handling various data sources, either single-modality or multi-modality, while maintaining accuracy and privacy. FRAMU's strengths include its adaptability in fluctuating data landscapes, its ability to unlearn outdated, private, or irrelevant data, and its support for continual model evolution without compromising privacy. Our experiments, conducted on both single-modality and multi-modality datasets, revealed that FRAMU significantly outperformed baseline models. Additional assessments of convergence behavior and optimization strategies further validate the framework's utility in federated learning applications. Overall, FRAMU advances Machine Unlearning by offering a robust, privacy-preserving solution that optimizes model performance while also addressing key challenges in dynamic data environments.

Recently, with the superior capacity for analyzing the multiplex graph data, self-supervised multiplex graph representation learning (SMGRL) has received much interest. However, existing SMGRL methods are still limited by the following issues: (i) they generally ignore the noisy information within each graph and the common information among different graphs, thus weakening the effectiveness of SMGRL, and (ii) they conduct negative sample encoding and complex pretext tasks for contrastive learning, thus weakening the efficiency of SMGRL. To solve these issues, in this work, we propose a new framework to conduct effective and efficient SMGRL. Specifically, the proposed method investigates the intra-graph and inter-graph decorrelation losses, respectively, for reducing the impact of noisy information within each graph and capturing the common information among different graphs, to achieve the effectiveness. Moreover, the proposed method does not need negative samples for the SMGRL and designs a simple pretext task, to achieve the efficiency. We further theoretically justify that our method achieves the maximal mutual information instead of directly conducting contrastive learning and theoretically justify that our method actually minimizes the multiplex graph information bottleneck, which guarantees the effectiveness. In addition, an extension for semi-supervised scenarios is proposed to fit the case that a few labels are provided in reality. Extensive experimental results verify the effectiveness and efficiency of the proposed method with respect to various downstream tasks.

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.

Semantic hashing enables computation and memory-efficient image retrieval through learning similarity-preserving binary representations. Most existing hashing methods mainly focus on preserving the piecewise class information or pairwise correlations of samples into the learned binary codes while failing to capture the mutual triplet-level ordinal structure in similarity preservation. In this article, we propose a novel Probability Ordinal-preserving Semantic Hashing (POSH) framework, which for the first time defines the ordinal-preserving hashing concept under a non-parametric Bayesian theory. Specifically, we derive the whole learning framework of the ordinal similarity-preserving hashing based on the maximum posteriori estimation, where the probabilistic ordinal similarity preservation, probabilistic quantization function, and probabilistic semantic-preserving function are jointly considered into one unified learning framework. In particular, the proposed triplet-ordering correlation preservation scheme can effectively improve the interpretation of the learned hash codes under an economical anchor-induced asymmetric graph learning model. Moreover, the sparsity-guided selective quantization function is designed to minimize the loss of space transformation, and the regressive semantic function is explored to promote the flexibility of the formulated semantics in hash code learning. The final joint learning objective is formulated to concurrently preserve the ordinal locality of original data and explore potentials of semantics for producing discriminative hash codes. Importantly, an efficient alternating optimization algorithm with the strictly proof convergence guarantee is developed to solve the resulting objective problem. Extensive experiments on several large-scale datasets validate the superiority of the proposed method against state-of-the-art hashing-based retrieval methods.

Different from previous imputation methods which impute missing values in the incomplete samples by using the information in the complete samples, this paper proposes a Date-drive Incremental imputation Model, DIM for short, which uses all available information in the data set to impute missing values economically, effectively, orderly, and iteratively. To this end, we propose a scoring rule to rank the missing features by taking into account both the economical criterion and the effective imputation information. The economical criterion takes both the imputation cost and the discriminative ability of the feature into account, while the effective imputation information enables to use all observed information in the data set including the imputed missing values to impute the left missing values. During the imputation process, our DIM first detects the neednot-impute samples for reducing the imputation cost and noise, and then selects the missing features with the top rank to impute first. The imputation process orderly imputes the missing features until all missing values are imputed or the imputation cost is exhausted. Experimental results on UCI data sets demonstrated the advantages of our proposed DIM, compared to the comparison methods, in terms of prediction accuracy and classification accuracy.

Referring expression comprehension is a task of identifying a text-related object or region in a given image by a natural language expression. In this task, it is essential to understand the expression sentence in multi-aspect and adapt it to region representations for generating the discriminative information. Unfortunately, previous approaches usually focus on the important words or phrases in the expression using self-attention mechanisms, which causes that they may fail to distinguish the target region from others, especially the similar regions. To address this problem, we propose a novel model, termed Multi-level Expression Guided Attention network (MEGA-Net). It contains a multi-level visual attention schema guided by the expression representations in different levels, i.e., sentence-level, word-level and phrase-level, which allows generating the discriminative region features and helps to locate the related regions accurately. In addition, to distinguish the similar regions, we design a two-stage structure, where we first select top-K candidate regions according to their matching scores in the first stage, then we apply an object comparison attention mechanism to learn the difference between the candidates for matching the target region. We evaluate the proposed approach on three popular benchmark datasets and the experimental results demonstrate that our model performs against state-of-the-art methods.

Zero-shot learning has been a highlighted research topic in both vision and language areas. Recently, generative methods have emerged as a new trend of zero-shot learning, which synthesizes unseen categories samples via generative models. However, the lack of fine-grained information in the synthesized samples makes it difficult to improve classification accuracy. It is also time-consuming and inefficient to synthesize samples and using them to train classifiers. To address such issues, we propose a novel Graph-based Variational Auto-Encoder for zero-shot learning. Specifically, we adopt knowledge graph to model the explicit inter-class relationships, and design a full graph convolution auto-encoder framework to generate the classifier from the distribution of the class-level semantic features on individual nodes. The encoder learns the latent representations of individual nodes, and the decoder generates the classifiers from latent representations of individual nodes. In contrast to synthesize samples, our proposed method directly generates classifiers from the distribution of the class-level semantic features for both seen and unseen categories, which is more straightforward, accurate and computationally efficient. We conduct extensive experiments and evaluate our method on the widely used large-scale ImageNet-21K dataset. Experimental results validate the efficacy of the proposed approach.

It has been demonstrated that the segmentation performance is highly dependent on both subspace preservation and graph connectivity. In the literature, the full connectivity method linearly represents each data point ( e.g., a pixel in one image) by all data points for achieving subspace preservation, while the sparse connectivity method was designed to linearly represent each data point by a set of data points for achieving graph connectivity. However, previous methods only focused on either subspace preservation or graph connectivity. In this article, we propose a Sparse Graph Connectivity (SGC) method for image segmentation to automatically learn the affinity matrix from the low-dimensional space of original data, which aims at simultaneously achieving subspace preservation and graph connectivity. To do this, the proposed SGC simultaneously learns a self-representation affinity matrix for subspace preservation and a sparse affinity matrix for graph connectivity, from the intrinsic low-dimensional feature space of high-dimensional original data. Meanwhile, the self-representation affinity matrix is pushed to be similar to the sparse affinity as well as be the final segmentation results. Experimental result on synthetic and real-image datasets showed that our SGC method achieved the best segmentation performance, compared to state-of-the-art segmentation methods.

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.

Previous multi-view spectral clustering methods are a two-step strategy, which first learns a fixed common representation (or common affinity matrix) of all the views from original data and then conducts k-means clustering on the resulting common affinity matrix. The two-step strategy is not able to output reasonable clustering performance since the goal of the first step (i.e., the common affinity matrix learning) is not designed for achieving the optimal clustering result. Moreover, the two-step strategy learns the common affinity matrix from original data, which often contain noise and redundancy to influence the quality of the common affinity matrix. To address these issues, in this paper, we design a novel One-step Multi-view Spectral Clustering (OMSC) method to output the common affinity matrix as the final clustering result. In the proposed method, the goal of the common affinity matrix learning is designed to achieving optimal clustering result and the common affinity matrix is learned from low-dimensional data where the noise and redundancy of original high-dimensional data have been removed. We further propose an iterative optimization method to fast solve the proposed objective function. Experimental results on both synthetic datasets and public datasets validated the effectiveness of our proposed method, comparing to the state-of-the-art methods for multi-view clustering.

Traditional graph clustering methods consist of two sequential steps, i.e., constructing an affinity matrix from the original data and then performing spectral clustering on the resulting affinity matrix. This two-step strategy achieves optimal solution for each step separately, but cannot guarantee that it will obtain the globally optimal clustering results. Moreover, the affinity matrix directly learned from the original data will seriously affect the clustering performance, since high-dimensional data are usually noisy and may contain redundancy. To address the above issues, this paper proposes a Low-rank Sparse Subspace (LSS) clustering method via dynamically learning the affinity matrix from low-dimensional space of the original data. Specifically, we learn a transformation matrix to project the original data to their low-dimensional space, by conducting feature selection and subspace learning in the sample self-representation framework. Then, we utilize the rank constraint and the affinity matrix directly obtained from the original data to construct a dynamic and intrinsic affinity matrix. Moreover, each of these three matrices is updated iteratively while fixing the other two. In this way, the affinity matrix learned from the low-dimensional space is the final clustering results. Extensive experiments are conducted on both synthetic and real datasets to show that our proposed LSS method outperforms the state-of-the-art clustering 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.

The K Nearest Neighbor (kNN) method has widely been used in the applications of data mining and machine learning due to its simple implementation and distinguished performance. However, setting all test data with the same k value in the previous kNN methods has been proven to make these methods impractical in real applications. This article proposes to learn a correlation matrix to reconstruct test data points by training data to assign different k values to different test data points, referred to as the Correlation Matrix kNN (CM-kNN for short) classification. Specifically, the least-squares loss function is employed to minimize the reconstruction error to reconstruct each test data point by all training data points. Then, a graph Laplacian regularizer is advocated to preserve the local structure of the data in the reconstruction process. Moreover, an ℓ 1 -norm regularizer and an ℓ 2, 1 -norm regularizer are applied to learn different k values for different test data and to result in low sparsity to remove the redundant/noisy feature from the reconstruction process, respectively. Besides for classification tasks, the kNN methods (including our proposed CM-kNN method) are further utilized to regression and missing data imputation. We conducted sets of experiments for illustrating the efficiency, and experimental results showed that the proposed method was more accurate and efficient than existing kNN methods in data-mining applications, such as classification, regression, and missing data imputation.

The problem of image categorization from zero or only a few training examples, called zero-shot learning, occurs frequently, but it has hardly been studied in computer vision research. To tackle this problem, mid-level semantic attributes are introduced to identify image categories. For example, one can construct a classifier for the giant panda category by enumerating its attributes (e.g., black, white and four-footed) even without providing giant panda training images. Recently, several studies have investigated to learn attribute classifiers, based on which new classes can be detected. However, an often-encountered problem is the limited number of training data due to the time-consuming manual annotation of the attributes. Also, using single feature is hard to detect some attributes, e.g., the HSV feature is not robust enough to predict 'tusk' or 'flies' attributes. In this paper, we propose a unified semi-supervised learning (SSL) framework that learns the attribute classifiers by utilizing multiple feature and exploring the correlations between images. Specifically, we learn an optimal graph which embeds the relationships among the data points more accurately. Then, this graph is used to generate a geometrical regularizers for a semi-supervised learning model to learn the attribute classifier by utilizing both labeled and unlabeled images. Afterward, new classes can be detected based on their attribute representation. The use of SSL can boost the performances of attribute classifiers with very few training examples, and the adoption of multiple features makes the attribute prediction more robust. Experimental results on a series of real benchmark data sets suggest that semi-supervised learning do enhance the performances of attribute prediction and zero-shot categorization, compared with state-of-the-art methods.

This paper takes manifold learning and regression simultaneously into account to perform unsupervised spectral feature selection. We first extract the bases of the data, and then represent the data sparsely using the extracted bases by proposing a novel joint graph sparse coding model, JGSC for short. We design a new algorithm TOSC to compute the resulting objective function of JGSC, and then theoretically prove that the proposed objective function converges to its global optimum via the proposed TOSC algorithm. We repeat the extraction and the TOSC calculation until the value of the objective function of JGSC satisfies pre-defined conditions. Eventually the derived new representation of the data may only have a few non-zero rows, and we delete the zero rows (a.k.a. zero-valued features) to conduct feature selection on the new representation of the data. Our empirical studies demonstrate that the proposed method outperforms several state-of-the-art algorithms on real datasets in term of the kNN classification performance.

Hash-based methods achieve fast similarity search by representing high-dimensional data with compact binary codes. However, both generating binary codes and encoding unseen data effectively and efficiently remain very challenging tasks. In this article, we focus on these tasks to implement approximate similarity search by proposing a novel hash based method named sparse hashing (SH for short). To generate interpretable (or semantically meaningful) binary codes, the proposed SH first converts original data into low-dimensional data through a novel nonnegative sparse coding method. SH then converts the low-dimensional data into Hamming space (i.e., binary encoding low-dimensional data) by a new binarization rule. After this, training data are represented by generated binary codes. To efficiently and effectively encode unseen data, SH learns hash functions by taking a-priori knowledge into account, such as implicit group effect of the features in training data, and the correlations between original space and the learned Hamming space. SH is able to perform fast approximate similarity search by efficient bit XOR operations in the memory of a modern PC with short binary code representations. Experimental results show that the proposed SH significantly outperforms state-of-the-art techniques.

Missing data imputation is a key issue in learning from incomplete data. Various techniques have been developed with great successes on dealing with missing values in data sets with homogeneous attributes (their independent attributes are all either continuous or discrete). This paper studies a new setting of missing data imputation, i.e., imputing missing data in data sets with heterogeneous attributes (their independent attributes are of different types), referred to as imputing mixed-attribute data sets. Although many real applications are in this setting, there is no estimator designed for imputing mixed-attribute data sets. This paper first proposes two consistent estimators for discrete and continuous missing target values, respectively. And then, a mixture-kernel-based iterative estimator is advocated to impute mixed-attribute data sets. The proposed method is evaluated with extensive experiments compared with some typical algorithms, and the result demonstrates that the proposed approach is better than these existing imputation methods in terms of classification accuracy and root mean square error (RMSE) at different missing ratios.

An association rule ArarrB is useful to predict that B will likely occur when A occurs. This is a classical association rule. In real world applications, such as bioinformatics and medical research, there are many follow correlations between itemsets A and B: B likely occurs n times after A occurred m times, wrote tom, BN>. We refer to this follow-correlation as P3.1 itemset-pairs because3, B1> like that in the example ( Example 2) should be uninterested in association analysis. This paper designs an efficient algorithm for identifying P3.1 itemset-pairs in sequential data. We experimentally evaluate our approach, and demonstrate that the proposed approach is efficient and promising.