Multi-modal knowledge graph completion (MMKGC) aims to infer missing entities of triples by leveraging heterogeneous information in knowledge graph (KG). However, existing approaches often struggle with inconsistent modality alignment, limited reasoning depth, and insufficient negative sample quality. In this work, we propose HFR-MKGC, a novel framework that integrates hierarchical modal fusion and Multimodal Large Language Model (MLLM) reasoning for robust and expressive MMKGC. Specifically, we introduce a relation-guided hierarchical modal fusion module, which conducts fine-grained intra-visual fusion and relation-guided cross-modal integration to yield rich entity representations. HFR-MKGC employs a fine-tuned MLLM to perform instruction-based triple reasoning, producing candidate entities for completion. Then, it constructs hard negative samples through textual perturbation by MLLM and visual feature augmentation with rotation and noise. HFR-MKGC optimizes the model via adversarial training. Extensive experiments on three MMKGC benchmarks demonstrate that our method outperforms state-of-the-art methods, validating its effectiveness in MMKGC.

Questionnaire data serve as a valuable resource across numerous scientific domains, offering insights into human behavior, health, and social trends. Traditional downsampling-based representation learning methods—such as standardization and one-hot encoding—reformat these data into tabular structures that inherently discard semantic richness and obscure inter-sample and inter-feature relationships. Consequently, advanced deep learning models often underperform compared to simpler approaches like gradient-boosted decision trees (GBDT), due to their limited capacity to extract meaningful representations from semantically sparse inputs. To address this limitation, we introduce SemantiQ, a novel upsampling-based representation learning framework that embeds questionnaire responses into a unified semantic space. Leveraging Retrieval-Augmented Generation (RAG) in conjunction with large language models (LLMs), SemantiQ transforms question text, option text, and external knowledge into semantically enriched natural language statements. These statements are then encoded into semantic embeddings, which are further refined through a three-stage training mechanism and test-time training (TTT), enabling the model to capture complex sample- and feature-wise dependencies. Extensive experiments on multiple real-world datasets demonstrate that SemantiQ consistently outperforms state-of-the-art baselines.

Spatial-temporal prediction plays a crucial role in various domains, including intelligent transportation and environmental monitoring. Although large language model has shown advantages in long-range dependency modeling and excellent generalization ability for forecasting, it has limited understanding of spatial-temporal features. Especially for spatial features, most existing methods still simplify the spatial-temporal prediction task into multiple independent temporal prediction tasks, failing to effectively encode the dynamic evolution of spatial relations. To address these problems, we propose ST-VLM (Spatial-Temporal Forecasting with Vision-Language Model), a novel framework that leverages visual representations to encode the dynamic spatial dependencies within spatial-temporal data and integrates multi-modal information to enhance prediction. This framework transforms spatial-temporal features into three modalities: vision, text, and time series, enhances cross-modal fusion through an attention-aware fusion mechanism in the first-layer of Vision-Language Model (VLM), optimizes multi-modal feature interaction via adaptive fine-tuning strategies. After fusion, the multi-modal embeddings are subsequently used for the final spatial-temporal prediction task. Extensive experiments demonstrate that ST-VLM achieves state-of-the-art performance across various datasets. In particular, the framework exhibits promising results in few-shot scenarios, verifying its strong generalization ability.

Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel ThoughtAugmented Interactive Recommender Agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Through comprehensive experiments conducted across multiple designed datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA's thought augmentation strategies endow the agent system with the ability to solve complex tasks while generalizing effectively on novel tasks, validating its potential as a foundational framework for agent systems, particularly in complex user intent scenarios.

The COVID-19 pandemic not only triggered a global health crisis but also amplified public panic through the rapid spread of misinformation. Understanding public sentiment and identifying the causes of sudden sentiment spikes is therefore critical for ensuring accurate information dissemination and guiding effective policymaking. However, mining such causes from social media remains challenging. Tweets collected during sentiment spike periods are often short, noisy, and dominated by repetitive background topics, making it difficult for existing topic models to separate emerging issues from long-standing discussions. To address these challenges, we propose the Sentiment Variation-aware Emerging Topics Mining Model (SVETM), a probabilistic graphical framework that leverages user sentiment variation between adjacent time windows as a guiding signal to distinguish emerging topics from background content. We further reformulate inference as a maximum a posteriori (MAP) problem and develop an efficient variational inference algorithm for scalable learning. Extensive experiments on a large-scale COVID-19 Twitter dataset demonstrate that SVETM outperforms strong baselines in terms of topic coherence, interpretability, and its ability to uncover the underlying causes of sentiment spikes.

Unsupervised federated learning for cross-modal retrieval has received increasing attention in recent years as it can free the requirement for annotations and avoid uploading original clients’ data to servers. Most existing methods focus on how to learn better local models and their aggregation to overcome data distribution drift across clients. Unlike prior works, we propose to address the data distribution problem by generating synthetic data, which can benefit existing federated learning methods. Specifically, we train a WGAN generator with three newly designed loss constraints on each client to improve the quality of the generated data. We first compute cluster prototypes to address the problem of lack of labels. Then, a direct contrastive loss between generated image and text features, an indirect contrastive loss with reference to cluster prototypes, and a Jensen-Shannon Divergence (JSD) loss also with reference to cluster prototypes work together to constrain the WGAN. The locally trained generators and local prototypes are sent to the server to generate and filter synthetic data with consideration of data distribution across all clients. The filtered data are used to train the aggregated global retrieval model, which is later sent to clients. The final global model becomes robust to all clients after several rounds of client-server iteration. Extensive experiments using four baselines across three datasets demonstrate that our method performs favourably against state-of-the-art methods.

To preserve user privacy in recommender systems, federated recommendation (FR) based on federated learning (FL) emerges, keeping the personal data on the local client and updating a model collaboratively. Unlike FL, FR has a unique sparse aggregation mechanism, where the embedding of each item is updated by only partial clients, instead of full clients in a dense aggregation of general FL. Recently, as an essential principle of FL, model security has received increasing attention, especially for Byzantine attacks, where malicious clients can send arbitrary updates. The problem of exploring the Byzantine robustness of FR is particularly critical since in the domains applying FR, e.g., e-commerce, malicious clients can be injected easily by registering new accounts. However, existing Byzantine works neglect the unique sparse aggregation of FR, making them unsuitable for our problem. Thus, we make the first effort to investigate Byzantine attacks on FR from the perspective of sparse aggregation, which is non-trivial: it is not clear how to define Byzantine robustness under sparse aggregations and design Byzantine attacks under limited knowledge/capability. In this paper, we reformulate the Byzantine robustness under sparse aggregation by defining the aggregation for a single item as the smallest execution unit. Then we propose a family of effective attack strategies, named Spattack, which exploit the vulnerability in sparse aggregation and are categorized along the adversary's knowledge and capability. Extensive experimental results demonstrate that Spattack can effectively prevent convergence and even break down defenses under a few malicious clients, raising alarms for securing FR systems.

With the rapid adoption of biometric authentication technologies, safeguarding users’ sensitive biometric data has become increasingly critical. Traditional centralized training methods pose significant risks due to exposure of raw biometric data. Federated learning offers a decentralized alternative but faces challenges from data and model heterogeneity, which can degrade performance and compromise privacy. To overcome these challenges, this work proposes Bio-IL, a decentralized and robust Biometric recognition system that integrates Isomerism Learning with heterogeneous models over a private blockchain infrastructure. The use of private blockchain ensures secure and tamper-resistant coordination of distributed training while safe-guarding data privacy. At the core of Bio-IL lies the novel IsoFus aggregation algorithm, an Isomerism Learning-based Fusion method that effectively combines heterogeneous local models and significantly improves recognition accuracy in realistic decentralized settings. Extensive experiments, with face recognition as a representative application, demonstrate that the proposed model outperforms baseline methods in both accuracy and robustness. This framework offers a scalable, secure, and adaptable solution for decentralized biometric authentication, making it well-suited for practical identity verification tasks.

Highly Heterogeneous Entity Alignment (HHEA) represents a more realistic application scenario of Entity Alignment (EA). This challenging task aims to align equivalent entities between highly heterogeneous knowledge graphs (HHKGs) with significant differences in structure, scale, and overlap. In practice, obtaining labeled data for HHEA is often difficult, necessitating research into unsupervised HHEA. This involves addressing several challenges, including the difficulty in capturing structural and semantic associations between HHKGs, the absence of explicit HHEA paradigms, and the high time and computational costs. Unfortunately, there is no solution for unsupervised HHEA. To bridge this gap, this paper formally investigates the unsupervised HHEA problem and proposes an effective unsupervised HHEA solution, AdaCoAgentEA, which addresses the challenges of unsupervised HHEA from the perspective of multi-agent collaboration. Specifically, we design an adaptive collaboration framework with three functional areas powered by multi-agent LLMs and small models, effectively eliminating dependence on labeled data while capturing structural and semantic correlations between HHKGs. Furthermore, we design a suite of optimization tools for AdaCoAgentEA, including meta-alignment mechanisms and communication protocols, which facilitate effective associations between HHKGs and provide explicit HHEA paradigms while reducing time and computational costs. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance in both unsupervised HHEA and classic EA tasks across five datasets, rivaling fully supervised models while maintaining high efficiency and scalability.

Long-term time series forecasting has been widely studied, yet two aspects remain insufficiently explored: the interaction learning between different frequency components and the exploitation of periodic characteristics inherent in timestamps. To address the above issues, we propose CFPT, a novel method that empowering time series forecasting through Cross-Frequency Interaction (CFI) and Periodic-Aware Timestamp Modeling (PTM). To learn cross-frequency interactions, we design the CFI branch to process signals in frequency domain and captures their interactions through a feature fusion mechanism. Furthermore, to enhance prediction performance by leveraging timestamp periodicity, we develop the PTM branch which transforms timestamp sequences into 2D periodic tensors and utilizes 2D convolution to capture both intra-period dependencies and inter-period correlations of time series based on timestamp patterns. Extensive experiments on multiple real-world benchmarks demonstrate that CFPT achieves state-of-the-art performance in long-term forecasting tasks. The code is publicly available at this repository: https://github.com/BUPT-SN/CFPT.

Personalized federated graph neural networks (PFGNN) are an emerging technology that allows multiple graph data owners to collaboratively train personalized models without sharing raw data. However, the Non-IID nature of graph data can cause the coupling of global and local knowledge parameters, which disrupts the optimization in personalized federated learning. Additionally, node neighbors may carry global and local knowledge, and their direct inclusion in training may introduce noise, degrading federated model performance. In this work, we propose the Adaptive Decoupling Personalized Federated Graph Neural Network (ADPFedGNN), which leverages multi-party collaboration to train personalized models for classifying local client graph nodes. We use two automatically updated masks and mutual information minimization to decouple global and local parameters in FGNN. We employ reinforcement learning to adaptively select appropriate neighbors for training global or local knowledge-related parameters while filtering out irrelevant nodes. We also design a personalized federated masked parameter aggregation mechanism that efficiently updates local personalized model parameters and aggregates the masked parameters. Experimental results on three public datasets demonstrate that ADPFedGNN outperforms existing methods, achieving average improvements of 5.66 percent, 5.83 percent, and 12.45 percent in ACC, F1, and Recall, respectively.

Federated Learning (FL) enables collaborative model training across distributed devices without sharing raw data. Hierarchical Federated Learning (HFL) is a new paradigm of FL that leverages the Edge Servers (ESs) layer as an intermediary to perform partial local model aggregation in proximity, reducing core network transmission overhead. However, HFL faces new challenges: (1) The two-stage aggregation process between client-edge and edge-cloud results in a dual-layer non-IID issue, which may significantly compromise model training accuracy. (2) The heterogeneity and mobility of clients further impact model training efficiency. To address these challenges, we propose a novel Clustered Semi-Asynchronous Hierarchical Federated Learning (CSAHFL) framework that integrates adaptive semi-asynchronous intra-cluster aggregation at client-edge layer and dynamic distribution-aware inter-cluster aggregation at edge-cloud layer, collaboratively enhancing model performance and scalability in heterogeneous and mobile environments. We conducte experiments under varying degrees of dual-layer non-IID in both static and high-mobility scenarios. The results demonstrate significant advantages of CSAHFL over representative state-of-the-art methods.

Large language models (LLMs) have demonstrated their strong capabilities in various domains, and have been recently integrated for graph analysis as graph language models (GLMs). With LLMs as the predictor, some GLMs can interpret unseen tasks described by natural language, and learn from a few examples in the prompts without parameter tuning, known as in-context learning (ICL). Another subset of GLMs utilizes abundant training labels to enhance model performance, known as instruction tuning. However, we argue that ICL on graphs has effectiveness issues due to fixed parameters and efficiency issues due to long context. Meanwhile, the large amount of labeled data required for instruction tuning can be difficult to obtain in real-world scenarios. To this end, we aim to introduce an extra parameter adaptation stage that can efficiently tailor GLMs to an unseen graph and task with only a few labeled examples, in exchange for better prediction accuracy and faster inference speed. For implementation, in this paper we propose GraphLAMA method, with its model backbone and learning schemes specialized for efficient tuning and inference. Specifically, for the model backbone, we use a graph neural network (GNN) with several well-designed components (e.g., hop encodings, gating modules) to transform nodes into the representation space of LLM tokens. Task instructions can then be represented as a mixture of node and language tokens. In the pre-training stage, all model parameters except for the LLM will be trained with different tasks (i.e., node matching, node classification, and link prediction) to capture general knowledge. In the adaptation stage, only a few pre-trained parameters will be updated based on few-shot examples. Extensive experiments on few/zero-shot node classification and summary generation show that our proposed GraphLAMA achieves state-of-the-art (SOTA) performance with 4.91% absolute improvement in accuracy. Compared with ICL, our inference speed can be 10 times faster under 5-shot setting. Our code is available on GitHub at https://github.com/BUPT-GAMMA/GraphLAMA.

Multimodal hashing stands as an efficient approach for multimodal retrieval, yet it frequently grapples with the challenge of misaligned representation spaces across different modalities. This misalignment can degrade the consistency and discrimination of multimodal representations, complicating the learning of effective representations for image and text pairs. Particularly, the task becomes arduous when the system must handle incomplete data while ensuring accurate and relevant retrieval outcomes. To address these challenges, we propose the Asymmetric Pre-aligned Anchor Contrastive Enhanced Diffusion Hashing Model (AADH) for Incomplete Multimodal Retrieval. Our model is specifically tailored to robustly manage multimodal incomplete data scenarios. Initially, we develop an Asymmetric Pre-alignment Strategy that utilizes asymmetric contrastive learning to preliminarily align the semantic disparities between various modalities. Subsequently, we propose an innovative Anchor Contrastive Reinforcement Diffusion Hashing Model, which integrates image and text modalities to varying extents during the reverse diffusion process. It constructs an anchor space that not only facilitates the learning of incomplete multimodal hashing representations through anchor contrastive learning but also leverages inter-modal and intra-modal contrastive learning to enhance the representations. Moreover, we effectively bridge the modality gap between different modal hash codes by employing the anchor space to constrain the representations of different modal hashes. By adjusting the initial noise of the diffusion model, we indirectly expand the data volume, which in turn bolsters the model's robustness. Our extensive experimental results across multiple datasets demonstrate that the proposed AADH model achieves state-of-the-art (SOTA) results.

The success of Graph Neural Networks (GNNs) in graph classification has heightened interest in explainable GNNs, particularly through graph rationalization. This method aims to enhance GNNs explainability by identifying subgraph structures (i.e., rationales) that support model predictions. However, existing methods often rely on centralized datasets, posing challenges in scenarios where data privacy is crucial, such as in molecular property prediction. Federated Learning (FL) offers a solution by enabling collaborative model training without sharing raw data. In this context, Federated Graph Rationalization emerges as a promising research direction. However, in each client, the rationalization methods often rely on client-specific shortcuts to compose rationales and make task predictions. Data heterogeneity, characterized by non-IID data across clients, exacerbates this problem, leading to poor prediction performance. To address these challenges, we propose the Environment-aware Data Augmentation (EaDA) method for Federated Graph Rationalization. EaDA comprises two main components: the Environment-aware Rationale Extraction (ERE) module and the Local-Global Alignment (LGA) module. The ERE module employs prototype learning to infer and share abstract environment information across clients, which are then aggregated to form a global environment. This information is used to generate counterfactual samples for local clients, enhancing the robustness of task predictions. The LGA module uses contrastive learning methods to align local and global rationale representations, mitigating performance degradation due to data heterogeneity. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of our approaches. Code is available at https://github.com/yuelinan/Codes-of-EaDA.

In the era of data-centric AI, the focus of recommender systems has shifted from model-centric innovations to data-centric approaches. The success of modern AI models is built on large-scale datasets, but this also results in significant training costs. Dataset distillation has emerged as a key solution, condensing large datasets to accelerate model training while preserving model performance. However, condensing discrete and sequentially correlated user-item interactions, particularly with extensive item sets, presents considerable challenges. This paper introduces TD3, a novel Tucker Decomposition based Dataset Distillation method within a meta-learning framework, designed for sequential recommendation. TD3 distills a fully expressive synthetic sequence summary from original data. To efficiently reduce computational complexity and extract refined latent patterns, Tucker decomposition decouples the summary into four factors: synthetic user latent factor, temporal dynamics latent factor, shared item latent factor, and a relation core that models their interconnections. Additionally, a surrogate objective in bi-level optimization is proposed to align feature spaces extracted from models trained on both original data and synthetic sequence summary beyond the naive performance matching approach. In the inner-loop, an augmentation technique allows the learner to closely fit the synthetic summary, ensuring an accurate update of it in the outer-loop. To accelerate the optimization process and address long dependencies, RaT-BPTT is employed for bi-level optimization. Experiments and analyses on multiple public datasets have confirmed the superiority and cross-architecture generalizability of the proposed designs. Codes are released at https://github.com/USTC-StarTeam/TD3.

Deep cross-modal hashing technology provides an effective and efficient cross-modal unified representation learning solution for cross-modal search. However, the existing methods neglect the implicit fine-grained multimodal knowledge relations between these modalities such as when the image contains information that is not directly described in the text. To tackle this problem, we propose a novel self-supervised multi-grained multi-modal knowledge graph contrastive hashing method for cross-modal search (CMGCH). Firstly, in order to capture implicit fine-grained cross-modal semantic associations, a multi-modal knowledge graph is constructed, which represents the implicit multimodal knowledge relations between the image and text as inter-modal and intra-modal semantic associations. Secondly, a cross-modal graph contrastive attention network is proposed to reason on the multi-modal knowledge graph to sufficiently learn the implicit fine-grained inter-modal and intra-modal knowledge relations. Thirdly, a cross-modal multi-granularity contrastive embedding learning mechanism is proposed, which fuses the global coarse-grained and local fine-grained embeddings by multihead attention mechanism for inter-modal and intra-modal contrastive learning, so as to enhance the cross-modal unified representations with stronger discriminativeness and semantic consistency preserving power. With the joint training of intra-modal and inter-modal contrast, the invariant and modal-specific information of different modalities can be maintained in the final unified cross-modal unified hash space. Extensive experiments on several cross-modal benchmark datasets demonstrate that the proposed CMGCH outperforms the state-of the-art methods.

Asynchronous federated learning (AFL) is a distributed machine learning technique that allows multiple devices to collaboratively train deep learning models without sharing local data. However, AFL suffers from low efficiency due to poor client model training quality and slow server model convergence speed, which are a result of the heterogeneous nature of both data and devices. To address these issues, we propose Efficient Asynchronous Federated Learning with Prospective Momentum Aggregation and Fine-Grained Correction (FedAC). Our framework consists of three key components. The first component is client weight evaluation based on temporal gradient, which evaluates the client weight based on the similarity between the client and server update directions. The second component is adaptive server update with prospective weighted momentum, which uses an asynchronous buffered update strategy and a prospective weighted momentum with adaptive learning rate to update the global model in server. The last component is client update with fine-grained gradient correction, which introduces a fine-grained gradient correction term to mitigate the client drift and correct the client stochastic gradient. We conduct experiments on real and synthetic datasets, and compare with existing federated learning methods. Experimental results demonstrate effective improvements in model training efficiency and AFL performance by our framework.

Cross-media hash retrieval are efficient and effective techniques for retrieval on multi-media database. The success of the Multimodal Large Models (MLM) provides a valuable direction to enhance the accuracy of multimodal hash retrieval, which achieves decent retrieval accuracy with finetuning the pretrained multimodal large models, but their massive model parameters significantly reduce retrieval efficiency. Knowledge Distillation (KD) methods enable small models to learn from the knowledge of larger models, achieving a reduction in model parameter count while ensuring a certain level of accuracy. However, current KD methods face challenges when applied in the multimodal domain, as it requires preserving the multimodal semantic information while minimizing accuracy degradation. To address these challenges, we propose a novel unsupervised multimodal graph contrastive semantic anchor space dynamic knowledge distillation network for cross-media hash retrieval (GASKN). Firstly, to obtain a multimodal semantic anchor space, we construct a large multimodal fusion teacher model using the BEiT-3 model as the backbone. This teacher model is capable of encoding data from different modalities, such as images and text, using the same multimodal encoder to acquire multimodal hash codes that contain rich information from both modalities simultaneously. Secondly, to ensure efficient retrieval capabilities for the student model, we utilize the ALBERT text encoding model and the BiFormer image encoding model as the compact student model's backbones. This allows us to build a lightweight student model with only a twentieth of the parameter count of the teacher model. We propose a dynamic knowledge distillation technique to transfer the multimodal semantic anchor space knowledge embedded in the multimodal large teacher model to the lightweight student model as much as possible. Thirdly, to further distill the structural knowledge of the semantic anchor space from the teacher model to the student model, we propose a graph attention contrastive learning mechanism, which enables structural semantic space learning, thereby mining implicit fine-grained cross-media semantic information. By evaluating our method using three widely-used datasets, we demonstrate that GASKN is able to significantly outperform existing state-of-the-art hashing algorithms.

Multi-view retrieval faces significant pressure due to the rapidly increasing multi-view information on the internet. The multi-view hashing method turns continuous features into compact information of fixed length and considerably improves retrieval efficiency. However, existing multi-view hashing methods neglect the bias produced during multi-view alignment and multi-label guidance processes. To address these issues, we introduce a novel multi-view hash method that learns compact hash codes. It first employs a multi-view double alignment module to align features from different views. Then, it utilizes a self-adjusted cross-attention fusion module to fuse these features. Finally, we propose a weighted contrastive learning module to learn more discriminative representations, smoothing the differences among all samples. Extensive experiments show that our method yields compact hash codes and outperforms state-of-the-art methods.

The heterogeneous information network (HIN), which contains rich semantics depicted by meta-paths, has emerged as a potent tool for mitigating data sparsity in recommender systems. Existing HIN-based recommender systems operate under the assumption of centralized storage and model training. However, real-world data is often distributed due to privacy concerns, leading to the semantic broken issue within HINs and consequent failures in centralized HIN-based recommendations. In this paper, we suggest the HIN is partitioned into private HINs stored on the client side and shared HINs on the server. Following this setting, we propose a federated heterogeneous graph neural network (FedHGNN) based framework, which facilitates collaborative training of a recommendation model using distributed HINs while protecting user privacy. Specifically, we first formalize the privacy definition for HIN-based federated recommendation (FedRec) in the light of differential privacy, with the goal of protecting user-item interactions within private HIN as well as users' high-order patterns from shared HINs. To recover the broken meta-path based semantics and ensure proposed privacy measures, we elaborately design a semantic-preserving user interactions publishing method, which locally perturbs user's high-order patterns and related user-item interactions for publishing. Subsequently, we introduce an HGNN model for recommendation, which conducts node- and semantic-level aggregations to capture recovered semantics. Extensive experiments on four datasets demonstrate that our model outperforms existing methods by a substantial margin (up to 34% in HR@10 and 42% in NDCG@10) under a reasonable privacy budget (e.g., ε=1).

Correlation filter (CF)-based approaches have been widely applied in online object tracking tasks for unmanned aerial vehicles (UAVs) due to their high computational efficiency and low memory consumption. One of the key steps is to perform correlation operations between the appearance model (AM) and the filter. However, as the difficulty in controlling the learning rate of the AM, most existing trackers are prone to causing degradation. In this paper, we propose a novel complementary AM (CAM) consisting of a primary model (PM) and a secondary model (SM). Specifically, the learning rates of the PM and SM are approximately complementary, allowing the CAM to consider both past and current information. Moreover, in order to take full advantage of historical information, a CAM-based reversibility reasoning approach is proposed for CF training. It can robustly handle the variations in object appearance. Then we further create a deep tracker by fusing convolutional features which demonstrates more outstanding performance. We also embed the CAM into two advanced trackers to validate the scalability of the CAM. Comprehensive experiments on six challenging UAV tracking benchmarks have indicated the superiority of our method compared to other 36 state-of-the-art CPU- and GPU-based trackers, with a speed of 45 FPS running on a cheap CPU.

The explosive growth of cyber attacks today, such as malware, spam, and intrusions, has caused severe consequences on society. Securing cyberspace has become a great concern for organizations and governments. Traditional machine learning based methods are extensively used in detecting cyber threats, but they hardly model the correlations between real-world cyber entities. In recent years, with the proliferation of graph mining techniques, many researchers have investigated these techniques for capturing correlations between cyber entities and achieving high performance. It is imperative to summarize existing graph-based cybersecurity solutions to provide a guide for future studies. Therefore, as a key contribution of this work, we provide a comprehensive review of graph mining for cybersecurity, including an overview of cybersecurity tasks, the typical graph mining techniques, and the general process of applying them to cybersecurity, as well as various solutions for different cybersecurity tasks. For each task, we probe into relevant methods and highlight the graph types, graph approaches, and task levels in their modeling. Furthermore, we collect open datasets and toolkits for graph-based cybersecurity. Finally, we present an outlook on the potential directions of this field for future research.

This brief is concerned with the problem of kernel adaptive filtering for a complex network. First, a coupled kernel least mean square (KLMS) algorithm is developed for each node to uncover its nonlinear measurement function by using a series of input-output data. Subsequently, an upper bound is derived for the step-size of the coupled KLMS algorithm to guarantee the mean square convergence. It is shown that the upper bound is dependent on the coupling weights of the complex network. Especially, an optimal step size is obtained to achieve the fastest convergence speed and a suboptimal step size is presented for the purpose of practical implementations. Besides, a coupled kernel recursive least square (KRLS) algorithm is further proposed to improve the filtering performance. Finally, simulations are provided to verify the validity of the theoretical results.

Graph Neural Networks (GNNs) have received considerable attention on graph-structured data learning for a wide variety of tasks. The well-designed propagation mechanism, which has been demonstrated effective, is the most fundamental part of GNNs. Although most of the GNNs basically follow a message passing manner, little effort has been made to discover and analyze their essential relations. In this article, we establish a surprising connection between different propagation mechanisms with an optimization problem. We show that despite the proliferation of various GNNs, in fact, their proposed propagation mechanisms are the optimal solutions of a generalized optimization framework with a flexible feature fitting function and a generalized graph regularization term. Actually, the optimization framework can not only help understand the propagation mechanisms of GNNs but also open up opportunities for flexibly designing new GNNs. Through analyzing the general solutions of the optimization framework, we provide a more convenient way for deriving corresponding propagation results of GNNs. We further discover that existing works usually utilize naïve graph convolutional kernels for feature fitting function or just utilize one-hop structural information (original topology graph) for graph regularization term. Correspondingly, we develop two novel objective functions considering adjustable graph kernels showing low-pass or high-pass filtering capabilities and one novel objective function considering high-order structural information during propagation, respectively. Extensive experiments on benchmark datasets clearly show that the newly proposed GNNs not only outperform the state-of-the-art methods but also have good ability to alleviate over-smoothing and further verify the feasibility for designing GNNs with the generalized unified optimization framework.

Video super-resolution (SR) reconstruction technology aims at obtaining high quality reconstruction of high-resolution (HR) video sequences by inferring the lost detailed information from their low-resolution (LR) counterparts. However, this technology is an ill-posed problem because significant detailed information is lost in the process of video degrading. The existing learning-based SR reconstruction methods can be adapted to a larger super-resolution factor, but it cannot be guaranteed that any low-resolution image block can find its corresponding high-resolution block matching in a limited-scale training set. Some noise and over smooth phenomenon usually exist while dealing with some unique features that rarely appear in a given training data set. The self-similarity based SR methods do not rely on accurate sub-pixel motion estimation and thus can be adapted to complex motion patterns. However, under conditions of insufficient internal similar blocks, some visual flaws are usually produced due to the mismatched internal instances.

Multi-view learning aims to fully exploit the information from multiple sources to obtain better performance than using a single view. However, real-world data often contains a lot of noise, which can have a large impact on multi-view learning. Therefore, it is necessary to identify noise contained in multi-view data to achieve robust and trusted classification. In this paper, we propose a robust trusted multi-view classification framework, RTMC. Our framework uses multi-view affinity and repellence encoding to learn effective latent encodings of multi-view data. We also propose a trust-aware discriminator to estimate trust scores by identifying noise contained in the data. We adopt prototype queues, which store latent encodings of different classes, to accurately identify the noise. Finally, trusted multi-view classification is proposed to jointly predict the trust scores of classification and achieve robust classification results through a trusted fusion strategy. RTMC is validated on six challenging multi-view datasets and the experimental results demonstrate the robustness and effectiveness of our method.

Out-of-distribution (OOD) detection, which aims to identify OOD samples from in-distribution (ID) ones in test time, has become an essential problem in machine learning. However, existing works are mostly conducted on Euclidean data, and the problem in graph-structured data remains under-explored. Several recent works begin to study graph OOD detection, but they all need to train a graph neural network (GNN) from scratch with high computational cost. In this work, we make the first attempt to endow a well-trained GNN with the OOD detection ability without modifying its parameters. To this end, we design a post-hoc framework with Adaptive Amplifier for Graph OOD Detection, named AAGOD, concentrating on data-centric manipulation. The insight of AAGOD is to superimpose a parameterized amplifier matrix on the adjacency matrix of each original input graph. The amplifier can be seen as prompts and is expected to emphasize the key patterns helpful for graph OOD detection, thereby enlarging the gap between OOD and ID graphs. Then well-trained GNNs can be reused to encode the amplified graphs into vector representations, and pre-defined scoring functions can further convert the representations into detection scores. Specifically, we design a Learnable Amplifier Generator (LAG) to customize amplifiers for different graphs, and propose a Regularized Learning Strategy (RLS) to train parameters with no OOD data required. Experiment results show that AAGOD can be applied on various GNNs to enable the OOD detection ability. Compared with the state-of-the-art baseline in graph OOD detection, on average AAGOD has 6.21% relative enhancement in AUC and a 34 times faster training speed. Code and data are available at https://github.com/BUPT-GAMMA/AAGOD.

In recent years, the issue of data privacy has attracted more and more attention. Federated learning is a practical solution to train the model while guaranteeing data privacy. It has two main characteristics: the first is that the data in the clients is usually non-IID, and the second is that the data of each client cannot be shared. However, due to the non-IID data of each client, the optimal solution of the client is often inconsistent with the global optimal solution. The non-IID data often causes the client to optimize along the local optimal direction and drift out of the global optimal solution during training. Due to the client drift problem, the server tends to converge slowly so that the overall communication efficiency of federated learning is usually limited. To improve the communication efficiency of federated learning, in this paper, we propose a new federated learning framework which integrates multi-level prospective correction factor in the training procedure of server and clients. We propose the global prospective correction factor in server aggregation to reduce model communication rounds and accelerate convergence. In client training, we introduce the local prospective correction factor to alleviate client drift. Both global and local prospective correction factors are integrated into a unified federated learning framework to further improve the communication efficiency. Extensive experiments conducted on several datasets demonstrate that our method can effectively improve the communication efficiency and is robust to different federated learning environments.

One big challenge to federated learning is the non-IID data distribution caused by imbalanced classes. Existing federated learning approaches tend to bias towards classes containing a larger number of samples during local updates, which causes unwanted drift in the local classifiers. To address this issue, we propose a classifier debiased federated learning framework named FedCD for non-IID data. We introduce a novel hierarchical prototype contrastive learning strategy to learn fine-grained prototypes for each class. The prototypes characterize the sample distribution within each class, which helps align the features learned in the representation layer of every client's local model. At the representation layer, we use fine-grained prototypes to rebalance the class distribution on each client and rectify the classification layer of each local model. To alleviate the bias of the classification layer of the local models, we incorporate a global information distillation method to enable the local classifier to learn decoupled global classification information. We also adaptively aggregate the class-level classifiers based on their quality to reduce the impact of unreliable classes in each aggregated classifier. This mitigates the impact of client-side classifier bias on the global classifier. Comprehensive experiments conducted on various datasets show that our method, FedCD, effectively corrects classifier bias and outperforms state-of-the-art federated learning methods.

Multi-view learning aims to leverage data acquired from multiple sources to achieve better performance compared to using a single view. However, the performance of multi-view learning can be negatively impacted by noisy or corrupted views in certain real-world situations. As a result, it is crucial to assess the confidence of predictions and obtain reliable learning outcomes. In this paper, we introduce CALM, an enhanced encoding and confidence evaluation framework for trustworthy multi-view classification. Our method comprises enhanced multi-view encoding, multi-view confidence-aware fusion, and multi-view classification regularization, enabling the simultaneous evaluation of prediction confidence and the yielding trustworthy classifications. Enhanced multi-view encoding takes advantage of cross-view consistency and class diversity to improve the efficacy of the learned latent representation, facilitating more reliable classification results. Multi-view confidence-aware fusion utilizes a confidence-aware estimator to evaluate the confidence scores of classification outcomes. The final multi-view classification results are then derived through confidence-aware fusion. To achieve reliable and accurate confidence scores, multivariate Gaussian distributions are employed to model the prediction distribution. The advantage of CALM lies in its ability to evaluate the quality of each view, reducing the influence of low-quality views on the multi-view fusion process and ultimately leading to improved classification performance and confidence evaluation. Comprehensive experimental results demonstrate that our method outperforms other trusted multi-view learning methods in terms of effectiveness, reliability, and robustness.

With the great popularity of Graph Neural Networks (GNNs), their robustness to adversarial topology attacks has received significant attention. Although many attack methods have been proposed, they mainly focus on fixed-budget attacks, aiming at finding the most adversarial perturbations within a fixed budget for target node. However, considering the varied robustness of each node, there is an inevitable dilemma caused by the fixed budget, i.e., no successful perturbation is found when the budget is relatively small, while if it is too large, the yielding redundant perturbations will hurt the invisibility. To break this dilemma, we propose a new type of topology attack, named minimum-budget topology attack, aiming to adaptively find the minimum perturbation sufficient for a successful attack on each node. To this end, we propose an attack model, named MiBTack, based on a dynamic projected gradient descent algorithm, which can effectively solve the involving non-convex constraint optimization on discrete topology. Extensive results on three GNNs and four real-world datasets show that MiBTack can successfully lead all target nodes misclassified with the minimum perturbation edges. Moreover, the obtained minimum budget can be used to measure node robustness, so we can explore the relationships of robustness, topology, and uncertainty for nodes, which is beyond what the current fixed-budget topology attacks can offer.

Change captioning is to describe the fine-grained change between a pair of images. The pseudo changes caused by viewpoint changes are the most typical distractors in this task, because they lead to the feature perturbation and shift for the same objects and thus overwhelm the real change representation. In this paper, we propose a viewpoint-adaptive representation disentanglement network to distinguish real and pseudo changes, and explicitly capture the features of change to generate accurate captions. Concretely, a position-embedded representation learning is devised to facilitate the model in adapting to viewpoint changes via mining the intrinsic properties of two image representations and modeling their position information. To learn a reliable change representation for decoding into a natural language sentence, an unchanged representation disentanglement is designed to identify and disentangle the unchanged features between the two position-embedded representations. Extensive experiments show that the proposed method achieves the state-of-the-art performance on the four public datasets. The code is available at https://github.com/tuyunbin/VARD.

Skyline is a primitive operation in multi-objective decision applications and there is a growing demand to support such operations over a data federation, where the entire dataset is separately held by multiple data providers (a.k.a., silos). Data federations notably increase the amount of data available for data-intensive applications such as commercial recommendation and location based services. Yet they also challenge the conventional implementation of skyline queries because the raw data cannot be shared within the federation and the secure computation cross silos can be two or three orders of magnitude slower than plaintext computation. These constraints render existing solutions inefficient on data federation. In this work, we propose a novel local dominance based framework for efficient skyline queries over a vertical data federation. We decompose the skyline query into plaintext local dominance computations and secure result aggregations, which can perform as many computations in plaintext as possible without compromising security. We further propose a dedicate private set intersection based algorithm to accelerate the query processing. Extensive evaluations on both synthetic and real-world datasets show that compared with general-purpose secure multi-party computation techniques, our solutions reduce the time cost by up to 35.4× and communication cost by two orders of magnitude respectively.

Graph Convolutional Networks (GCNs) have gained great popularity in tackling various analytic tasks on graph and network data. However, some recent studies raise concerns about whether GCNs can optimally integrate node features and topological structures in a complex graph. In this paper, we first present an experimental investigation. Surprisingly, our experimental results clearly show that the capability of the state-of-the-art GCNs in fusing node features and topological structures is distant from optimal or even satisfactory. The weakness may severely hinder the capability of GCNs in some classification tasks, since GCNs may not be able to adaptively learn some deep correlation information between topological structures and node features. Can we remedy the weakness and design a new type of GCNs that can retain the advantages of the state-of-the-art GCNs and, at the same time, enhance the capability of fusing topological structures and node features substantially? We tackle the challenge and propose anAdaptiveMulti-channelGraphConvolutionalNetwork for semi-supervised classification (AM-GCN). The central idea is that we extract the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and use the attention mechanism to learn adaptive importance weights of the embeddings. However, considering that the input topology and feature structure in AM-GCN are still predefined and fixed, once the properties of graph structures are not consistent with tasks, the fusion performance of AM-GCN will be hindered from the beginning. Therefore, we need to adjust the structure and further propose theLabelPropagation guidedMulti-channelGraphConvolutionalNetwork (LPM-GCN). LPM-GCN introduces edge weights learning on both topology and feature spaces to improve structural homophily, which can better promote the fusion process of graph convolutional networks. Our extensive experiments on benchmark data sets clearly show that our proposed models extract the most correlated information from both node features and topological structures substantially, and improves the classification accuracy with a clear margin.

Deep cross-media hashing technology provides an efficient cross-media representation learning solution for cross-media search. However, the existing methods do not consider both fine-grained semantic features and semantic structures to mine implicit cross-media semantic associations, which leads to weaker semantic discrimination and consistency for cross-media representation. To tackle this problem, we propose a novel semantic structure enhanced contrastive adversarial hash network for cross-media representation learning (SCAHN). Firstly, in order to capture more fine-grained cross-media semantic associations, a fine-grained cross-media attention feature learning network is constructed, thus the learned saliency features of different modalities are more conducive to cross-media semantic alignment and fusion. Secondly, for further improving learning ability of implicit cross-media semantic associations, a semantic label association graph is constructed, and the graph convolutional network is utilized to mine the implicit semantic structures, thus guiding learning of discriminative features of different modalities. Thirdly, a cross-media and intra-media contrastive adversarial representation learning mechanism is proposed to further enhance the semantic discriminativeness of different modal representations, and a dual-way adversarial learning strategy is developed to maximize cross-media semantic associations, so as to obtain cross-media unified representations with stronger discriminativeness and semantic consistency preserving power. Extensive experiments on several cross-media benchmark datasets demonstrate that the proposed SCAHN outperforms the state-of-the-art methods.

Incomplete multi-view clustering is a challenging task which aims to partition the unlabeled incomplete multi-view data into several clusters. The existing incomplete multi-view clustering methods neglect to utilize the diversified correlations inherent in data and handle the noise contained in different views. To address these issues, we propose a Robust Diversified Graph Contrastive Network (RDGC) for incomplete multi-view clustering, which integrates multi-view representation learning and diversified graph contrastive regularization into a unified framework. Multi-view unified and specific encoding network is developed to fuse different views into a unified representation, which can flexibly estimate the importance of views for incomplete multi-view data. Robust diversified graph contrastive regularization is proposed which captures the diversified data correlations to improve the discriminating power of the learned representation and reduce the information loss caused by the view missing problem. Moreover, our method can effectively resist the influence of noise and unreliable views by leveraging the robust contrastive learning loss. Extensive experiments conducted on four multi-view clustering datasets demonstrate the superiority of our method over the state-of-the-art methods.

Prohibited item detection is an important problem in e-commerce, where the goal is to detect illegal items online for evading risks and stemming crimes. Traditional solutions usually mine evidence from individual instances, while current efforts try employing advanced Graph Neural Networks (GNN) to utilize multiple risk-relevant structures of items. However, it still remains two essential challenges, including weak structure and weak supervision. This work proposes the Risk Graph Structure Learning model (RGSL) for prohibited item detection. RGSL first introduces structure learning into large-scale risk graphs, to reduce noisy connections and add similar pairs. It then designs the pairwise training mechanism, which transforms the detection process as a metric learning from candidates to their similar prohibited items. Furthermore, RGSL generates risk-aware item representations and searches risk-relevant pairs for structure learning iteratively. We test RGSL on three real-world scenarios, and the improvements to baselines are up to 21.91% in AP and 18.28% in MAX-F1. Meanwhile, RGSL has been deployed on an e-commerce platform, and the improvements to traditional solutions are up to 23.59% in [email protected] and 6.52% in [email protected]

The rapid development of the social network has brought great convenience to people's lives. A large amount of cross-media big data, such as text, image, and video data, has been accumulated. A cross-media search can facilitate a quick query of information so that users can obtain helpful content for social networks. However, cross-media data suffer from semantic gaps and sparsity in social networks, which bring challenges to cross-media searches. To alleviate the semantic gaps and sparsity, we propose a cross-media search method based on complementary attention and generative adversarial networks (CAGS). To obtain high-quality feature representations, we build a complementary attention mechanism containing the focused and unfocused features of images to realize the consistent association of cross-media data in social networks. By designing the cross-media adversarial learning process, we can obtain a common semantic representation of cross-media data and further alleviate the semantic gap and sparsity issues for social networks. Finally, we perform a similarity calculation to realize an accurate cross-media search. We construct four search tasks utilizing two standard cross-media data sets to verify the search performance of the proposed CAGS.

Predicting the development trend of future scientific research not only provides a reference for researchers to understand the development of the discipline, but also provides support for decision-making and fund allocation for decision-makers. The continuous growth of scientific publications has brought challenges to track the development trends of scientific research topics. The existing topic trend prediction methods have proved that the research topic trend of a publication is influenced by other peer publications. However, they ignore the fact that the research topics of different publications belong to different research topic space. Moreover, the existing topic prediction methods do not fully consider the interactive influence among publications that the research topic of one publication affects the topics of other publications, it is also influenced by the research topics of other publications. In line with this, this paper proposes a scientific research topic trend prediction model based on multi-long short-term memory (multi-LSTM) and Graph Convolutional Network. Specifically, multiple LSTMs are employed to map research topics of different publications into their respective topic space. Then, the graph convolutional neural network is applied to learn the scientific influence context of each publication, so that the research topic of each publication not only integrates the influence of neighbor nodes, but also considers the influence of the neighbors of the neighbor node on the research topic of the publication, so as to more accurately fuse scientific influence context of research topic of peer publications. Experiments results on the data set of scientific research papers in the field of artificial intelligence and data mining demonstrate that the model improves the prediction precision and achieves the state-of-the-art research topic trend prediction effect compared with the other baseline models.

For large-scale machine learning tasks, distributing data in multiple clients, and using distributed optimization algorithms with a parameter server can accelerate the training process. The federated average algorithm has been widely used for distributed optimization via training local models in parallel and aggregating local models in a server to obtain the global model. To further improve the performance of the federated average algorithm, a novel federated learning algorithm have been proposed in this article by embedding a lazy strategy in the distributed Adam-type algorithm. In the proposed algorithm, the learning rate is adjusted adaptively in local update and lazy update strategy is applied on the second-order momentum of clients to make the learning rate identical. The convergence of the proposed algorithm is provided for both convex and nonconvex loss functions. Experiments have been conducted on MNIST digit recognition data set and CIFAR-10 data set. Experimental results show that the proposed algorithm can significantly reduce the communication overhead, thereby reduce the training time by 60% for CIFAR-10 data set, and the proposed algorithm achieve better performance than the federated average algorithm and its momentum version.

Deblurring images captured in dynamic scenes is challenging as the motion blurs are spatially varying caused by camera shakes and object movements. In this paper, we propose a spatially varying neural network to deblur dynamic scenes. The proposed model is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN). The RNN is used as a deconvolution operator on feature maps extracted from the input image by one of the CNNs. Another CNN is used to learn the spatially varying weights for the RNN. As a result, the RNN is spatial-aware and can implicitly model the deblurring process with spatially varying kernels. To better exploit properties of the spatially varying RNN, we develop both one-dimensional and two-dimensional RNNs for deblurring. The third component, based on a CNN, reconstructs the final deblurred feature maps into a restored image. In addition, the whole network is end-to-end trainable. Quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against the state-of-the-art deblurring algorithms.

Random walk is widely used in many graph analysis tasks, especially the first-order random walk. However, as a simplification of real-world problems, the first-order random walk is poor at modeling higher-order structures in the data. Recently, second-order random walk-based applications (e.g., Node2vec, Second-order PageRank) have become attractive. Due to the complexity of the second-order random walk models and memory limitations, it is not scalable to run second-order random walk-based applications on a single machine. Existing disk-based graph systems are only friendly to the first-order random walk models and suffer from expensive disk I/Os when executing the second-order random walks. This paper introduces an I/O-efficient disk-based graph system for the scalable second-order random walk of large graphs, called GraSorw. First, to eliminate massive light vertex I/Os, we develop a bi-block execution engine that converts random I/Os into sequential I/Os by applying a new triangular bi-block scheduling strategy, the bucket-based walk management, and the skewed walk storage. Second, to improve the I/O utilization, we design a learning-based block loading model to leverage the advantages of the full-load and on-demand load methods. Finally, we conducted extensive experiments on six large real datasets as well as several synthetic datasets.. The empirical results demonstrate that the end-to-end time cost of popular tasks in GraSorw is reduced by more than one order of magnitude compared to the existing disk-based graph systems.

The increasing concerns on data security limit the sharing of data distributedly stored at multiple data owners and impede the scale of spatial queries over big urban data. In response, data federation systems have emerged to perform secure queries across multiple data owners leveraging secure multi-party computation. However, existing systems are designed for relational data. They are highly inefficient on spatial queries and limited in usability. In this demonstration, we introduce Hu-Fu, the first data federation system for secure spatial queries with high efficiency and usability. Hu-Fu is designed from the perspectives of the query user and the data owner for high usability and decomposes a spatial query into as many plaintext operators and as few secure operators as possible for high efficiency. We demonstrate the deployment and usage of Hu-Fu via cross-company taxi-calling, a popular smart city application.

To address the problems in the existing video super-resolution methods, such as noise, over smooth and visual artifacts, which are caused by the reliance on limited external training or mismatch of internal similarity patch instances, this study proposes a novel video super-resolution reconstruction algorithm based on deep learning and spatio-temporal feature similarity (DLSS-VSR). The video super-resolution reconstruction mechanism with the joint internal and external constraints is established utilizing the complementary advantages of both external deep correlation mapping learning and internal spatio-temporal nonlocal self-similarity prior constraint. A deep learning model based on deep convolutional neural network is constructed to learn the nonlinear correlation mapping between low-resolution and high-resolution video frame patches. A novel spatio-temporal feature similarity calculation method is proposed, which considers both internal video spatio-temporal self-similarity and external clean nonlocal similarity. For the internal spatio-temporal feature self-similarity, we improve the accuracy and robustness of similarity matching by proposing a similarity measure strategy based on spatio-temporal moment feature similarity and structural similarity. The external nonlocal similarity prior constraint is learned by the patch group-based Gaussian mixture model. The time efficiency for spatio-temporal similarity matching is further improved based on saliency detection and region correlation judgment strategy, which achieves a better tradeoff between super-resolution accuracy and speed. Experimental results demonstrate that the DLSS-VSR algorithm achieves competitive super-resolution quality compared to other state-of-the-art algorithms in both subjective and objective evaluations.

Incomplete multi-view clustering aims to cluster samples with missing views, which has drawn more and more research interest. Although several methods have been developed for incomplete multi-view clustering, they fail to extract and exploit the comprehensive global and local structure of multi-view data, so their clustering performance is limited. This paper proposes a Clustering-induced Adaptive Structure Enhancing Network (CASEN) for incomplete multi-view clustering, which is an end-to-end trainable framework that jointly conducts multi-view structure enhancing and data clustering. Our method adopts multi-view autoencoder to infer the missing features of the incomplete samples. Then, we perform adaptive graph learning and graph convolution on the reconstructed complete multi-view data to effectively extract data structure. Moreover, we use multiple kernel clustering to integrate the global and local structure for clustering, and the clustering results in turn are used to enhance the data structure. Extensive experiments on several benchmark datasets demonstrate that our method can comprehensively obtain the structure of incomplete multi-view data and achieve superior performance compared to the other methods.

Convolutional neural networks have achieved excellent performance on face recognition (FR) by learning the high discriminative features with advanced loss functions. These improved loss functions share the similar idea for maximizing inter-class variance or minimizing intra-class variance. In this article, from a different perspective, we consider enlarging the inter-class variance by directly penalizing weight vectors of last fully connected layer, which represent the center of classes. To the end, we propose Orthogonality loss as an elegant penalty item appends to common classification loss to learn the discriminative representations. The main idea is that in order for weight vectors to be discriminative, it should be as close as possible to be orthogonal to each other in the vector space. More specifically, the optimization objective of Orthogonality loss is the first moment and second moment of cosine similarity of weight vectors. We performed the empirical studies through simulating the long-tail datasets to show the generalization ability of the proposed approach on long-tail distribution datasets. Further, extensive experiments on large-scale face recognition benchmarks including the Labeled Face in the Wild (LFW), the IARPA Janus Benchmark A (IJB-A), IJB-B, IJB-C, MegaFace Challenge 1 (MF1) and MS-Celeb-1M Low-shot Learning demonstrated that Orthogonality loss outperforms strong baselines, which showcases the extensive suitability and effectiveness of Orthogonality loss.

Social networks are critical sources for event detection thanks to the characteristics of publicity and dissemination. Unfortunately, the randomness and semantic sparsity of the social network text bring significant challenges to the event detection task. In addition to text, time is another vital element in reflecting events since events are often followed for a while. Therefore, in this article, we propose a novel method named Multi-View Graph Attention Network (MVGAN) for event detection in social networks. It enriches event semantics through both neighbor aggregation and multi-view fusion in a heterogeneous social event graph. Specifically, we first construct a heterogeneous graph by adding the hashtag to associate the isolated short texts and describe events comprehensively. Then, we learn view-specific representations of events through graph convolutional networks from the perspectives of text semantics and time distribution, respectively. Finally, we design a hashtag-based multi-view graph attention mechanism to capture the intrinsic interaction across different views and integrate the feature representations to discover events. Extensive experiments on public benchmark datasets demonstrate that MVGAN performs favorably against many state-of-the-art social network event detection algorithms. It also proves that more meaningful signals can contribute to improving the event detection effect in social networks, such as published time and hashtags.

Recently, recommender systems play a pivotal role in alleviating the problem of information overload. Latent factor models have been widely used for recommendation. Most existing latent factor models mainly utilize the interaction information between users and items, although some recently extended models utilize some auxiliary information to learn a unified latent factor for users and items. The unified latent factor only represents the characteristics of users and the properties of items from the aspect of purchase history. However, the characteristics of users and the properties of items may stem from different aspects, e.g., the brand-aspect and category-aspect of items. Moreover, the latent factor models usually use the shallow projection, which cannot capture the characteristics of users and items well. Deep neural network has shown tremendous potential to model the non-linearity relationship between users and items. It can be used to replace shallow projection to model the complex correlation between users and items. In this paper, we propose a Neural network based Aspect-level Collaborative Filtering model (NeuACF) to exploit different aspect latent factors. Through modelling the rich object properties and relations in recommender system as a heterogeneous information network, NeuACF first extracts different aspect-level similarity matrices of users and items, respectively, through different meta-paths, and then feeds an elaborately designed deep neural network with these matrices to learn aspect-level latent factors. Finally, the aspect-level latent factors are fused for the top-N recommendation. Moreover, to fuse information from different aspects more effectively, we further propose NeuACF++ to fuse aspect-level latent factors with self-attention mechanism. Extensive experiments on three real world datasets show that NeuACF and NeuACF++ significantly outperform both existing latent factor models and recent neural network models.

In multitarget tracking systems, it is usually assumed that each measurement is generated with respect to a single target. This is not always true for generating relative state measurements or cross-target information in a coupled fashion. This note is concerned with the problem of distributed filtering for multitarget tracking systems with coupled measurements. By representing the coupling features of the target states in the measurements as a directed graph, a modified Kalman consensus filter (KCF) is proposed for a target-dependent augmented system whose state vector consists of in-going neighborhood targets. To analyze the performance of the modified KCF in a directed graph, a sufficient condition is derived to guarantee the boundedness of the estimation errors in the mean square sense. Numerical studies are provided to verify the applicability of the KCF.

We provide new criterion and a class of strict Lyapunov functions (SLFs) for time-varying systems (TVSs) with zero homogeneity. The definition of homogeneous auxiliary system is given, where it is assumed that certain homogeneous functions are admitted with their derivatives, in terms of the error systems, bounded by periodic functions. Based on the homogeneous auxiliary system, sufficient conditions of uniform asymptotical stability for TVSs are formulated using the homogeneity framework. Unlike existing results, where non-SLFs or persistence of excitation condition are required, our criterion is greatly relaxed for broad classes of systems. The utility of our result is illustrated by case-study of pendulum stability with quasi-periodical frictions.

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries.In this paper, we develop a neural abstractive multidocument summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries.Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents.Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries.Furthermore, pre-trained language models can be easily combined with our model, which further improve the summarization performance significantly.Empirical results on the WikiSum and MultiNews dataset show that the proposed architecture brings substantial improvements over several strong baselines.

Current local density-based anomaly detection methods are limited in that the local density estimation and the neighborhood density estimation are not accurate enough for complex and large databases, and the detection performance depends on the size parameter of the neighborhood. In this paper, we propose a new kernel function to estimate samples' local densities and propose a weighted neighborhood density estimation to increase the robustness to changes in the neighborhood size. We further propose a local kernel regression estimator and a hierarchical strategy for combining information from the multiple scale neighborhoods to refine anomaly factors of samples. We apply our general anomaly detection method to image saliency detection by regarding salient pixels in objects as anomalies to the background regions. Local density estimation in the visual feature space and kernel-based saliency score propagation in the image enable the assignment of similar saliency values to homogenous object regions. Experimental results on several benchmark datasets demonstrate that our anomaly detection methods overall outperform several state-of-art anomaly detection methods. The effectiveness of our image saliency detection method is validated by comparison with several state-of-art saliency detection methods.

Cross-media search from large-scale social network big data has become increasingly valuable in our daily life because it can support querying different data modalities. Deep hash networks have shown high potential in achieving efficient and effective cross-media search performance. However, due to the fact that social network data often exhibit text sparsity, diversity, and noise characteristics, the search performance of existing methods often degrades when dealing with this data. In order to address this problem, this article proposes a novel end-to-end cross-media semantic correlation learning model based on a deep hash network and semantic expansion for social network cross-media search (DHNS). The approach combines deep network feature learning and hash-code quantization learning for multimodal data into a unified optimization architecture, which successfully preserves both intramedia similarity and intermedia correlation, by minimizing both cross-media correlation loss and binary hash quantization loss. In addition, our approach realizes semantic relationship expansion by constructing the image-word relation graph and mining the potential semantic relationship between images and words, and obtaining the semantic embedding based on both internal graph deep walk and an external knowledge base. Experimental results demonstrate that DHNS yields better cross-media search performance on standard benchmarks.

The edge computing-based 5G networks have the advantages in efficiently offloading the large-scale Internet traffic, which is considered to be a promising architecture to alleviate the conflict between transmission performance and quality of experience (QoE). However, due to the unreliability of service providers and the mutual interference between wireless channels in 5G networks, it is still difficult for existing solutions to provide satisfactory multimedia services for mobile users. In response to these crucial challenges, this paper proposes a reliable and efficient multimedia service optimization framework named “REMSO” hereby, including a two-stage joint optimization procedure. Specifically, a reliable video service mechanism is first constructed to help the mobile users distinguish the credible and economic service BSs. Afterwards, an efficient wireless resource allocation strategy is established to achieve low latency and energy efficient video service optimization. In particular, the Stackelberg and potential game models are leveraged to achieve these optimization objectives. Finally, extensive simulations corroborate that our REMSO framework can deliver prominent performance advantages in terms of the reliability and efficiency when comparing with the state-of-the-art solutions.

In modern pavement management systems, pavement roughness is an important indicator of pavement performance, and it reflects the smoothness of pavement surface. International Roughness Index (IRI) is the de-facto metric to quantitatively analyze the roughness of pavement surface. The pavement with high IRI not only reduces the lifetime of vehicles, but also raises the risk of car accidents. Accurate prediction of IRI becomes a key task for the pavement management system, and it helps the transportation department refurbish the pavement in time. However, existing models are proposed on top of small datasets, and have poor performance. Besides, they only consider cross-sectional features of the pavements without any time-series information. In order to better capture the latent relationship between the cross-sectional and time-series features, we propose a novel feature fusion LSTM-BPNN model. LSTM-BPNN first learns the cross-sectional and time-series features with two neural networks separately, then it fuses both features via an attention mechanism. Experimental results on a high-quality real-world dataset clearly demonstrate that the new model outperforms existing considerable alternatives.

The last decade has witnessed the emergence and popularity of event-based social networks (EBSNs), which extend online social networks to the physical world. Fundamental on EBSN platforms is to appropriately assign EBSN users to events they are interested to attend, known as event-participant arrangement. Previous event-participant arrangement studies either fail to avoid conflicts among events or ignore the social interactions among participants. In this work, we propose a new event-participant arrangement problem called Interaction-aware Global Event-Participant Arrangement (IGEPA). It globally optimizes arrangements between events and participants to avoid conflicts in events, and not only accounts for user interests, but also encourages socially active participants to join. To solve the IGEPA problem, we design an approximation algorithm which has an approximation ratio of at least 1\4. Experimental results validate the effectiveness of our solution.

Incomplete view information often results in failure cases of the conventional multi-view methods. To address this problem, we propose a Deep Correlated Predictive Subspace Learning (DCPSL) method for incomplete multi-view semi-supervised classification. Specifically, we integrate semi-supervised deep matrix factorization, correlated subspace learning, and multi-view label prediction into a unified framework to jointly learn the deep correlated predictive subspace and multi-view shared and private label predictors. DCPSL is able to learn proper subspace representation that is suitable for class label prediction, which can further improve the performance of classification. Extensive experimental results on various practical datasets demonstrate that the proposed method performs favorably against the state-of-the-art methods.

Cross-media search is useful for getting more comprehensive and richer information about social network hot topics or events. To solve the problems of feature heterogeneity and semantic gap of different media data, existing deep cross-media quantization technology provides an efficient and effective solution for cross-media common semantic representation learning. However, due to the fact that social network data often exhibits semantic sparsity, diversity, and contains a lot of noise, the performance of existing cross-media search methods often degrades. To address the above issue, this paper proposes a novel fine-grained cross-media representation learning model with deep quantization attention network for social network cross-media search (CMSL). First, we construct the image-word semantic correlation graph, and perform deep random walks on the graph to realize semantic expansion and semantic embedding learning, which can discover some potential semantic correlations between images and words. Then, in order to discover more fine-grained cross-media semantic correlations, a multi-scale fine-grained cross-media semantic correlation learning method that combines global and local saliency semantic similarity is proposed. Third, the fine-grained cross-media representation, cross-media semantic correlations and binary quantization code are jointly learned by a unified deep quantization attention network, which can preserve both inter-media correlations and intra-media similarities, by minimizing both cross-media correlation loss and binary quantization loss. Experimental results demonstrate that CMSL can generate high-quality cross-media common semantic representation, which yields state-of-the-art cross-media search performance on two benchmark datasets, NUS-WIDE and MIR-Flickr 25k.

Semi-supervised classification receives increasing interests because it can predict class labels based on both limited labeled and sufficient unlabeled data. In this letter, we propose a deep constrained low-rank subspace learning (DCLSL) method for multi-view semi-supervised classification. Specifically, we integrate deep constrained matrix factorization, low-rank subspace learning, and class label learning into a unified objective function to jointly learn data similarity matrices and class label matrix. DCLSL is able to obtain the discriminative subspace representation of each view and effectively aggregate similarity matrices of multiple views, resulting in better classification performance. Experimental results on various datasets demonstrate the effectiveness of our method.

Camera sensors often fail to capture clear images or videos in a poorly lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the global content and the salient structures of the clear image in a unified network. More specifically, the content stream estimates the global content of the low-light input through an encoder-decoder network. However, the encoder in the content stream tends to lose some structure details. To remedy this, we propose a novel spatially variant recurrent neural network (RNN) as an edge stream to model edge details, with the guidance of another auto-encoder. The experimental results show that the proposed network favorably performs against the state-of-the-art low-light image enhancement algorithms.

Short text analysis is a challenging task as far as the sparsity and limitation of semantics. The semantic extension approach learns the meaning of a short text by introducing external knowledge. However, for the randomness of short text descriptions in microblogs, traditional extension methods cannot accurately mine the semantics suitable for the microblog theme. Therefore, we use the prominent and refined hashtag information in microblogs as well as complex social relationships to provide implicit guidance for semantic extension of short text. Specifically, we design a deep hash model based on social and conceptual semantic extension, which consists of dual semantic extension and deep hashing representation. In the extension method, the short text is first conceptualized to achieve the construction of hashtag graph under conceptual space. Then, the associated hashtags are generated by correlation calculation based on the integration of social relationships and concepts to extend the short text. In the deep hash model, we use the semantic hashing model to encode the abundant semantic features and form a compact and meaningful binary encoding. Finally, extensive experiments demonstrate that our method can learn and represent the short texts well by using more meaningful semantic signal. It can effectively enhance and guide the semantic analysis and understanding of short text in microblogs.

In data-intensive cloud collaboration services with tens of thousands of users and million-level resources, means of providing personalized and trust-aware services quickly and simultaneously is a challenging issue. In this paper, we propose Per-trust, a trust-aware and fast resource matchmaking scheme for personalized QoS guaranteeing in collaboration cloud service. First, an integrated and trust-aware service broking architecture is proposed across the collaborative cloud computing environment; this architecture can provide trust computing and personalized resource matchmaking capacities. Then, a resource clustering method is proposed based on the multidimensional properties of cloud resources; this method can accurately, quickly meet the personalized requirements of users. Finally, an innovative algorithm is proposed for the trust computing of service resources based on real-time and dynamic monitoring of data, thereby quickly and effectively providing trust-aware resource matchmaking. Different from existing methods, which focus only on QoS and trust issues, our approach adds a resource clustering step before QoS and trust evaluation. Three key components are organically combined, namely, service broking architecture, resource clustering, and security and QoS-related trust computing. To the best of our knowledge, this paper is the first to construct an integrated solving scheme for cloud resource matchmaking that can simultaneously satisfy the trustworthiness and personalization required by users. Theoretical and experimental results verify the effectiveness of the proposed scheme.

Tumor clustering is a powerful approach for cancer class discovery which is crucial to the effective treatment of cancer. Many traditional clustering methods such as NMF-based models, have been widely used to identify tumors. However, they cannot achieve satisfactory results. Recently, subspace clustering approaches have been proposed to improve the performance by dividing the original space into multiple low-dimensional subspaces. Among them, low rank representation is becoming a popular approach to attain subspace clustering. In this paper, we propose a novel Low Rank Subspace Clustering model via Discrete Constraint and Hypergraph Regularization (DHLRS). The proposed method learns the cluster indicators directly by using discrete constraint, which makes the clustering task simple. For each subspace, we adopt Schatten -norm to better approximate the low rank constraint. Moreover, Hypergraph Regularization is adopted to infer the complex relationship between genes and intrinsic geometrical structure of gene expression data in each subspace. Finally, the molecular pattern of tumor gene expression data sets is discovered according to the optimized cluster indicators. Experiments on both synthetic data and real tumor gene expression data sets prove the effectiveness of proposed DHLRS.

This paper studies the state estimation problem for nonlinearly coupled complex networks. A variance-constrained state estimator is developed by using the structure of the extended Kalman filter, where the gain matrix is determined by optimizing an upper bound matrix for the estimation error covariance despite the linearization errors and coupling terms. Compared with the existing estimators for linearly coupled complex networks, a distinct feature of the proposed estimator is that the gain matrix can be derived separately for each node by solving two Riccati-like difference equations. By using the stochastic analysis techniques, sufficient conditions are established which guarantees the state estimation error is bounded in mean square. A numerical example is provided to show the effectiveness and applicability of the proposed estimator.

Online peer-to-peer (P2P) lending is an emerging wealth-management service for individuals, which allows lenders to directly bid and invest on the listings created by borrowers without going through any traditional financial intermediaries. As a nonbank financial platform, online P2P lending tends to have both high volatility and liquidity. Therefore, it is of significant importance to discern the hidden market states of the listings (e.g., hot and cold), which open venues for enhancing business analytics and investment decision making. However, the problem of market state modeling remains pretty open due to many technical and domain challenges, such as the dynamic and sequential characteristics of listings. To that end, in this paper, we present a focused study on market state modeling and analysis for online P2P lending. Specifically, we first propose two enhanced sequential models by extending the Bayesian hidden Markov model (BHMM), namely listing-BHMM (L-BHMM) and listing and marketing-BHMM (LM-BHMM), for learning the latent semantics between listings' market states and lenders' bidding behaviors. Particularly, L-BHMM is a straightforward model that only considers the local observations of a listing itself, while LM-BHMM considers not only the listing information but also the global information of current market (e.g., the competitive and complementary relations among listings). Furthermore, we demonstrate several motivating applications enabled by our models, such as bidding prediction and herding detection. Finally, we construct extensive experiments on two real-world data sets and make some deep analysis on bidding behaviors, which clearly validate the effectiveness of our models in terms of different applications and also reveal some interesting business findings.

Past research on facial expressions have used relatively limited datasets, which makes it unclear whether current methods can be employed in real world. In this paper, we present a novel database, RAF-DB, which contains about 30000 facial images from thousands of individuals. Each image has been individually labeled about 40 times, then EM algorithm was used to filter out unreliable labels. Crowdsourcing reveals that real-world faces often express compound emotions, or even mixture ones. For all we know, RAF-DB is the first database that contains compound expressions in the wild. Our cross-database study shows that the action units of basic emotions in RAF-DB are much more diverse than, or even deviate from, those of lab-controlled ones. To address this problem, we propose a new DLP-CNN (Deep Locality-Preserving CNN) method, which aims to enhance the discriminative power of deep features by preserving the locality closeness while maximizing the inter-class scatters. The benchmark experiments on the 7-class basic expressions and 11-class compound expressions, as well as the additional experiments on SFEW and CK+ databases, show that the proposed DLP-CNN outperforms the state-of-the-art handcrafted features and deep learning based methods for the expression recognition in the wild.

This article studies the problem of state estimation for stochastic systems with unknown inputs. To reduce the communication cost from the sensor to the remote processor, an event‐triggered communication mechanism is proposed in terms of an event generator function for the innovation vectors. The event‐triggered estimator is developed by introducing an input term in the steady‐state Kalman filter for the corresponding nominal system. The input gain matrix is determined by treating the nominal estimator error dynamics as the desired performance. It is shown that the estimation error is bounded in mean square under certain conditions. A numerical example is provided to verify the effectiveness of the proposed estimator.

Sociologists have long converged that the evolution of a Social Networking Service(SNS) is driven by the interplay between users' preferences (reflected in user-item interaction behavior) and the social network structure (reflected in user-user interaction behavior). Nevertheless, traditional approaches either modeled these two kinds of behaviors in isolation or relied on a static assumption of a SNS. Thus, it is still unclear how do the roles of the dynamic social network structure and users' historical preferences affect the evolution of SNSs. Furthermore, can transforming the underlying social theories in the platform evolution modeling process benefit both behavior prediction tasks? In this paper, we incorporate the underlying social theories to explain and model the evolution of users' two kinds of behaviors in SNSs. Specifically, we present two kinds of representations for users' behaviors: a direct (latent) representation that presumes users' behaviors are represented directly (latently) by their historical behaviors. Under each representation, we associate each user's two kinds of behaviors with two vectors at each time. Then, for each representation, we propose the corresponding learning model to fuse the interplay between users' two kinds of behaviors. Finally, extensive experimental results demonstrate the effectiveness of our proposed models for both user preference prediction and social link suggestion.

This paper deals with finite-time consensus problems for multiagent systems that are subject to hybrid cooperative and antagonistic interactions. Two consensus protocols are constructed by employing the nearest neighbor rule. It is shown that under the presented protocols, the states of all agents can be guaranteed to reach an agreement in a finite time regarding consensus values that are the same in modulus but may not be the same in sign. In particular, the second protocol can enable all agents to reach a finite-time consensus with a settling time that is not dependent upon the initial states of agents. Simulation results are given to demonstrate the effectiveness and finite-time convergence of the proposed consensus protocols.

A novel super‐resolution (SR) reconstruction algorithm based on multisource bidirectional similarity and non‐local similarity matching for multi‐exposure dynamic image sequences is proposed in this study. First, luminance compensation for multi‐exposure dynamic images is implemented based on multisource bidirectional similarity. Then, combining a self‐adaptive regional correlation evaluation strategy and a weighting strategy based on pseudo‐Zernike moment feature similarity and structural similarity yields a novel and robust non‐local similarity matching scheme (PZ‐NSM) to learn non‐local similarity priors between low‐ and high‐resolution dynamic image patches at different spatio‐temporal scales without additional training. Finally, SR reconstruction is implemented based on PZ‐NSM and spatio‐temporal trans‐scale fusion of non‐local similarities between dynamic images. The proposed algorithm does not rely on accurate estimation of subpixel motion and can therefore be adapted to more complex motion patterns. It has high rotation invariance effectiveness and is robust to noise and illumination. Experimental results demonstrate that the proposed algorithm outperforms existing algorithms in terms of both subjective and objective evaluations.

Video data fusion should simultaneously take into account both temporal and spatial dimensions, and therefore a novel spatiotemporal video‐fusion algorithm based on motion compensation in the wavelet‐transform domain is proposed in this study. The fusion method incorporates motion compensation and the wavelet transform, thus making full use of spatial geometric information and inter‐frame temporal information of input videos. The proposed method improves the temporal stability and consistency of the fused video compared to other existing individual frame‐based fusion methods. The algorithm first decomposes the image frames which have been processed by an optic flow motion‐compensation approach and then develops a spatiotemporal energy‐based fusion rule to merge input videos. Experimental results demonstrate that the proposed fusion algorithm has superior visual and quantitative performance to traditional individual‐frame‐based and state‐of‐the‐art three‐dimensional‐transform‐based methods.

Images are complex multimedia data that contain rich semantic information. Currently, most of image annotation algorithms are only annotating the object semantics of images. There are still many challenges on high-level semantic image annotation. The major issues are the lack of effective modeling method for the high-level semantics of images and the lack of efficient dynamic update mechanism for the training set. To address these issues, we propose a high-level semantic annotation method based on hot Internet topics in this paper. There are two independent sub tasks in our method: dynamic update of the training set based on hot Internet topics and search-based image annotation. In the first sub task, we propose to model the abstract semantics of images based on three relationships: image–to–image similarity relationship, topic–to–topic co-occurrence relationship, and image–to–topic relevance relationship. Through the complex graph clustering, the hot Internet topics are extracted for images with consistent visual and semantic contents. Then the dynamic update mechanism will update the original training set with the new topics and images. It avoids the huge computing cost in traditional update methods and does not need to re-calculate the whole mapping relationship between the semantic concepts and visual features. In the second sub task, given a query image, it first searches for similar candidates in the annotated training set via visual features. Then the hypergraph modeling and spectral clustering are exploited to filter out the images with irrelevant semantics. The keywords will be extracted for annotation from the remaining images according to an annotation probability. Extensive experiments have been conducted and the results demonstrate that our algorithm could achieve better annotation performance than the state-of-the-art algorithms. And the update mechanism could extend the training set efficiently so that the coverage of the semantics in the training set wouldn’t be obsolete.

This paper deals with the consensus tracking control issues of multiagent systems and aims to solve them as accurately as possible over a finite time interval through an iterative learning approach. Based on the iterative rule, distributed algorithms are proposed for every agent using its nearest neighbor knowledge, for which the robustness problem is addressed against initial state shifts, disturbances, and switching topologies. These uncertainties are dynamically changing not only along the time axis but also the iteration axis. It is shown that the matrix norm conditions can be developed to achieve the convergence of the considered consensus tracking objectives, for which necessary and sufficient conditions are presented in terms of linear matrix inequalities to guarantee their feasibility in the sense of the spectral norm. Furthermore, simulation examples are given to illustrate the effectiveness and robustness of the obtained consensus tracking results.

In cloud computing, trust management is more important than ever before in the use of information and communication technologies. Owing to the dynamic nature of the cloud, continuous monitoring on trust attributes is necessary to enforce service‐level agreements. This study presents Cloud‐Trust, an adaptive trust management model for efficiently evaluating the competence of a cloud service based on its multiple trust attributes. In Cloud‐Trust, two kinds of adaptive modelling tools (rough set and induced ordered weighted averaging (IOWA) operator) are organically integrated and successfully applied to trust data mining and knowledge discovery. Using rough set to discover knowledge from trust attributes makes the model surpass the limitations of traditional models, in which weights are assigned subjectively. Moreover, Cloud‐Trust uses the IOWA operator to aggregate the global trust degree based on time series, thereby enabling better real‐time performance. Experimental results show that Cloud‐Trust converges more rapidly and accurately than do existing approaches, thereby verifying that it can effectively take on trust measurement tasks in cloud computing.

Object representation based on local features is a topical subject in the domain of image understanding and computer vision. We discuss the defects of global features in present methods and the advantages of local features in object recognition, and briefly explore state-of-the-art recognition methods using local features, especially the main approaches of local feature extraction and object representation. To clearly explain these methods, the problem of local feature extraction is divided into feature region detection, feature region description, and feature space optimization. The main components and merits of these steps are presented. Technologies for object presentation are classified into three types: vector space, sliding window, and structure relationship models. Future development trends are discussed briefly.

The resource efficiency and dependability of a trust system are the most fundamental requirements for any wireless sensor network (WSN). However, existing trust systems developed for WSNs are incapable of satisfying these requirements because of their high overhead and low dependability. In this work, we proposed a lightweight and dependable trust system (LDTS) for WSNs, which employ clustering algorithms. First, a lightweight trust decision-making scheme is proposed based on the nodes' identities (roles) in the clustered WSNs, which is suitable for such WSNs because it facilitates energy-saving. Due to canceling feedback between cluster members (CMs) or between cluster heads (CHs), this approach can significantly improve system efficiency while reducing the effect of malicious nodes. More importantly, considering that CHs take on large amounts of data forwarding and communication tasks, a dependability-enhanced trust evaluating approach is defined for cooperations between CHs. This approach can effectively reduce networking consumption while malicious, selfish, and faulty CHs. Moreover, a self-adaptive weighted method is defined for trust aggregation at CH level. This approach surpasses the limitations of traditional weighting methods for trust factors, in which weights are assigned subjectively. Theory as well as simulation results shows that LDTS demands less memory and communication overhead compared with the current typical trust systems for WSNs.

This paper is devoted to the consensus tracking issue on multiagent systems. Instead of enabling the networked agents to reach an agreement asymptotically as the time tends to infinity, the consensus tracking between agents is considered to be derived on a finite time interval as accurately as possible. We thus propose a learning algorithm with a gain operator to be determined. If the gain operator is designed in the form of a polynomial expression, a necessary and sufficient condition is obtained for the networked agents to accomplish the consensus tracking objective, regardless of the relative degree of the system model of agents. Moreover, the H∞ analysis approach is introduced to help establish conditions in terms of linear matrix inequalities (LMIs) such that the resulting processes of the presented learning algorithm can be guaranteed to monotonically converge in an iterative manner. The established LMI conditions can also enable the iterative learning processes to converge with an exponentially fast speed. In addition, we extend the learning algorithm to address the relative formation problem for multiagent systems. Numerical simulations are performed to demonstrate the effectiveness of learning algorithms in achieving both consensus tracking and relative formation objectives for the networked agents.

This paper is devoted to solving formation problems of multi-agent systems with higher-order dynamics. By using the iterative learning control (ILC) approaches, effective distributed algorithms are developed to enable all agents in directed graphs to achieve the desired relative formations perfectly over a finite-time interval. It is shown that the graph theory can be combined to develop conditions for both asymptotic stability and monotonic convergence of multi-agent formation ILC. Simulation results are finally given to verify our theoretical study.

Iterative learning control (ILC) is a kind of effective data-driven method that is developed based on online and/or offline input/output data. The main purpose of this paper is to supply a unified 2-D analysis approach for both continuous-time and discrete-time ILC systems with relative degree. It is shown that the 2-D Roesser system framework can be established for general ILC systems regardless of relative degree, under which convergence conditions can be provided to guarantee both asymptotic stability and monotonic convergence of the ILC processes. In particular, conditions for the monotonic convergence of ILC can be given in terms of linear matrix inequalities, and formulas for the updating law can be derived simultaneously. Simulation results are presented to illustrate the effectiveness of ILC determined through the 2-D design approach in dealing with the higher order relative degree problem of ILC systems, as well as the robustness of such ILC against uncertainties.