检索结果-内蒙古大学图书馆

IEEE Transactions on Fuzzy systems 2025年

作者： Wu, Haijie Lin, Weiwei Chen, Yuehong Shi, Fang Shen, Wangbo Chen, C. L. Philip South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Pengcheng Laboratory Shenzhen518066 China Guangdong Polytechnic Normal University School of Mathematics and Systems Science Guangzhou510665 China South China Agricultural University College of Mathematics and Informatics Guangzhou510642 China South China University of Technology School of Computer Science and Engineering Guangzhou511442 China

The fuzzy broad learning system (FBLS) has received increasing attention due to its ability to quickly train from broad learning systems (BLS) and interpretability with fuzzy inference. However, the randomness of BLS brings instability to the training performance of the model, so the hyperparameters of the model are crucial for its performance. Currently, many FBLS use grid search to determine hyperparameters. However, grid search brings longer search time and the parameters obtained have randomness, which may not necessarily be the optimal hyperparameters. In response to these challenges, this paper proposes a fuzzy broad learning system with automatic determination of hyperparameters (ADHFBLS). We construct a novel FBLS based on the interval type-2 fuzzy set and design an incremental learning algorithm for rules and enhancement nodes to support rapid model expansion. Meanwhile, a heuristic hyperparameter automatic optimization algorithm is designed to overcome the randomness and long optimization time of grid search. Experiments have shown that ADHFBLS has higher accuracy and shorter model tuning time compared to some state-of-the-art models based on FBLS. © 1993-2012 IEEE.

关键词： Adversarial machine learning

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shi, Liangtao Liu, Ting Hu, Xiantao Hu, Yue Yin, Quanjun Hong, Richang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of systems engineering National University of Defense Technology Hunan Province Changsha410073 China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210014 China

Visual grounding aims to ground an image region through natural language, which heavily relies on cross-modal alignment. Most existing methods transfer visual/linguistic knowledge separately by fully fine-tuning uni-modal pre-trained models, followed by a simple stack of visual-language transformers for multimodal fusion. However, these approaches not only limit adequate interaction between visual and linguistic contexts, but also incur significant computational costs. Therefore, to address these issues, we explore a step-wise multimodal fusion and adaption framework, namely SwimVG. Specifically, SwimVG proposes step-wise multimodal prompts (Swip) and cross-modal interactive adapters (CIA) for visual grounding, replacing the cumbersome transformer stacks for multimodal fusion. Swip can improve the alignment between the vision and language representations step by step, in a token-level fusion manner. In addition, weight-level CIA further promotes multimodal fusion by cross-modal interaction. Swip and CIA are both parameter-efficient paradigms, and they fuse the cross-modal features from shallow to deep layers gradually. Experimental results on four widely-used benchmarks demonstrate that SwimVG achieves remarkable abilities and considerable benefits in terms of efficiency. Our code is available at https://***/liuting20/SwimVG. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

DDPS: Dynamic Differential Pricing-Based Edge Offloading System With Energy Harvesting Devices

学校读者我要写书评

暂无评论

IEEE Transactions on Network science and engineering 2025年

作者： Xue, Hai Xia, Yun Xiong, Neal N. Zhang, Di Pei, Songwen University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Sul Ross State University Department of Computer Science and Mathematics AlpineTX79830 United States Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China Zhengzhou University Henan International Joint Laboratory of Intelligent Health Information System Zhengzhou450001 China Zhengzhou University National Engineering Laboratory for Internet Medical Systems and Applications Zhengzhou450001 China

Mobile edge computing (MEC) mitigates the energy and computation burdens on mobile users (MUs) by offloading tasks to the network edge. To optimize MEC server utilization through effective resource allocation, a well-designed pricing strategy is indispensable. In this paper, we propose a dynamic differential pricing scheme (DDPS) for an edge offloading scenario with energy harvesting devices, which determines prices based on computing resource usage to enhance edge server (ES) utilization. First, an offloading decision algorithm is proposed to balance harvested and consumed energy, determining whether and how much data to offload. Second, a Stackelberg game-based differential pricing algorithm is proposed to optimize computing resource allocation for MUs and reallocate surplus resources to delay-sensitive devices. Extensive simulations are conducted to demonstrate the effectiveness of the proposed DDPS scheme. Specifically, in comparison to the existing best-performing pricing scheme, for different task arrival rates, DDPS can achieve a 5.3% decrease in average execution delay, a 1.7% increase in ES utility (Userver, which represents the payment from MUs minus penalties for discarded tasks), and a 2.1% increase in the average ratio of service for MUs. In addition, DDPS also improves 2.8% Userver on average with different ES computation capacities. © 2025 IEEE. All rights reserved.

关键词： Mobile edge computing

A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qiu, Yuyang Kim, Kibaek Yousefian, Farzad Department of Industrial and systems Engineering Rutgers University New BrunswickNJ08901 United States Mathematics and Computer Science Division Argonne National Laboratory LemontIL60439 United States

Heterogeneity in federated learning (FL) is a critical and challenging aspect that significantly impacts model performance and convergence. In this paper, we propose a novel framework by formulating heterogeneous FL as a hierarchical optimization problem. This new framework captures both local and global training process through a bilevel formulation and is capable of the following: (i) addressing client heterogeneity through a personalized learning framework;(ii) capturing pre-training process on server’s side;(iii) updating global model through nonstandard aggregation;(iv) allowing for nonidentical local steps;and (v) capturing clients’ local constraints. We design and analyze an implicit zeroth-order FL method (ZO-HFL), provided with nonasymptotic convergence guarantees for both the server-agent and the individual client-agents, and asymptotic guarantees for both the server-agent and client-agents in an almost sure sense. Notably, our method does not rely on standard assumptions in heterogeneous FL, such as the bounded gradient dissimilarity condition. We implement our method on image classification tasks and compare with other methods under different heterogeneous settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

Asymptotics-Aware Multi-View Subspace Clustering

学校读者我要写书评

暂无评论

IEEE Transactions on Multimedia 2025年

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytechnic University School of Computer and Information Wuhu241000 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

Recently, multi-view subspace clustering has attracted extensive attention due to the rapid increase of multi-view data in many real-world applications. The main goal of this task is to learn a common representation of multiple subspaces from the given multi-view data, and most existing methods usually directly merge multiple groups of features by the single-step integration. However, there may exist large disparities among different views of the data, and thus the conventional single-step practice can hardly obtain a generally consistent feature representation for the multi-view data. To overcome this challenge, we present a novel approach dubbed "Asymptotics-Aware Multi-view Subspace Clustering (A2 MSC)"to pursue a consistent feature representation in a multi-step way, which iteratively conducts the data recovery to gradually reduce the differences between pairwise views. Specifically, we construct an asymptotic learning rule to update the feature representation, and the iteration result converges to a consistent feature vector for characterizing each instance of the original multi-view data. After that, we utilize such a new feature representation to learn a clustering-oriented similarity matrix via minimizing a self-expressive objective, and we also design the corresponding optimization algorithm to solve it with convergence guarantees. Theoretically, we prove that the learned asymptotic representation effectively integrates multiple views, thereby ensuring the effective handling of multi-view data. Empirically, extensive experimental results demonstrate the superiority of our proposed A2 MSC over the state-of-the-art multi-view subspace clustering approaches. © 2025 IEEE.

关键词： Data assimilation

Visual Sensor-Based Trajectory Multimodality Prediction via Anchor-Free Query Attention Network

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wang, Ruiping Cheng, Jun Yu, Junzhi Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore639798 Singapore Peking University College of Engineering Beijing100871 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

As a core component of intelligent surveillance and autonomous driving systems, visual sensor-based trajectory multimodality prediction can significantly improve their perception and decision-making capabilities. Numerous existing trajectory prediction methods are dedicated to enhance prediction performance. However, they still fail to effectively model the complex spatiotemporal interactions among pedestrians and trajectory multimodality. To address the above challenges, this article presents one new trajectory multimodality prediction method via anchor-free query-based attention network, which can more effectively capture spatiotemporal interactions and model trajectory multimodality. First, the initial trajectory proposal module employs target-centered query-based attention to capture complex spatiotemporal interactions and generate multiple trajectory proposals corresponding to the multiple modes of the future trajectory, which allows the model to use different interaction information when decoding trajectory points at different time steps. Second, the novel trajectory refinement module utilizes the learnable trajectory proposals to construct proposal-level interaction mechanisms to refine future trajectories. Experimental results conducted on ETH and UCY datasets demonstrate that the proposed model can provide the state-of-the-art prediction performance. © 1963-2012 IEEE.

关键词： Prediction models

Matrix Factorization for Inferring Associations and Missing Links

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Barron, Ryan Eren, Maksim E. Truong, Duc P. Matuszek, Cynthia Wendelberger, James Dorn, Mary F. Alexandrov, Boian Theoretical Division Los Alamos National Laboratory United States Information Systems and Modeling Los Alamos National Laboratory United States Department of Computer Science and Electrical Engineering University of Maryland Baltimore County United States Computer Computational and Statistical Sciences Los Alamos National Laboratory United States

Missing link prediction is a method for network analysis, with applications in recommender systems, biology, social sciences, cybersecurity, information retrieval, and Artificial Intelligence (AI) reasoning in Knowledge Graphs. Missing link prediction identifies unseen but potentially existing connections in a network by analyzing the observed patterns and relationships. In proliferation detection, this supports efforts to identify and characterize attempts by state and non-state actors to acquire nuclear weapons or associated technology - a notoriously challenging but vital mission for global security. Dimensionality reduction techniques like Non-Negative Matrix Factorization (NMF) and Logistic Matrix Factorization (LMF) are effective but require selection of the matrix rank parameter, that is, of the number of hidden features, k, to avoid over/under-fitting. We introduce novel Weighted (WNMFk), Boolean (BNMFk), and Recommender (RNMFk) matrix factorization methods, along with ensemble variants incorporating logistic factorization, for link prediction. Our methods integrate automatic model determination for rank estimation by evaluating stability and accuracy using a modified bootstrap methodology and uncertainty quantification (UQ), assessing prediction reliability under random perturbations. Additionally, we incorporate Otsu threshold selection and k-means clustering for Boolean matrix factorization, comparing them to coordinate descent-based Boolean thresholding. Our experiments highlight the impact of rank k selection, evaluate model performance under varying test-set sizes, and demonstrate the benefits of UQ for reliable predictions using abstention. We validate our methods on three synthetic datasets (Boolean and Gaussian distributed) and benchmark them against LMF and symmetric LMF (symLMF) on five real-world protein-protein interaction networks, showcasing an improved prediction performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Xinghao Niu, Jianwei Liu, Xuefeng Zhu, Guogang Zhang, Jiayuan Tang, Shaojie School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems School of Management Center for AI Business Innovation University at Buffalo BuffaloNY United States

Federated Prototype Learning (FedPL) has emerged as an effective strategy for handling data heterogeneity in Federated Learning (FL). In FedPL, clients collaboratively construct a set of global feature centers (prototypes), and let local features align with these prototypes to mitigate the effects of data heterogeneity. The performance of FedPL highly depends on the quality of prototypes. Existing methods assume that larger inter-class distances among prototypes yield better performance, and thus design different methods to increase these distances. However, we observe that while these methods increase prototype distances to enhance class discrimination, they inevitably disrupt essential semantic relationships among classes, which are crucial for model generalization. This raises an important question: how to construct prototypes that inherently preserve semantic relationships among classes? Directly learning these relationships from limited and heterogeneous client data can be problematic in FL. Recently, the success of pretrained language models (PLMs) demonstrates their ability to capture semantic relationships from vast textual corpora. Motivated by this, we propose FedTSP, a novel method that leverages PLMs to construct semantically enriched prototypes from the textual modality, enabling more effective collaboration in heterogeneous data settings. We first use a large language model (LLM) to generate fine-grained textual descriptions for each class, which are then processed by a PLM on the server to form textual prototypes. To address the modality gap between client image models and the PLM, we introduce trainable prompts, allowing prototypes to adapt better to client tasks. Extensive experiments demonstrate that FedTSP mitigates data heterogeneity while significantly accelerating convergence. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

Online Covariance Matrix Estimation in Sketched Newton Methods

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kuang, Wei Anitescu, Mihai Na, Sen Department of Statistics The University of Chicago United States Mathematics and Computer Science Division Argonne National Laboratory United States School of Industrial and Systems Engineering Georgia Institute of Technology United States

Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and robustness. In this paper, we study an online sketched Newton method that leverages a randomized sketching technique to perform an approximate Newton step in each iteration, thereby eliminating the computational bottleneck of second-order methods. While existing studies have established the asymptotic normality of sketched Newton methods, a consistent estimator of the limiting covariance matrix remains an open problem. We propose a fully online covariance matrix estimator that is constructed entirely from the Newton iterates and requires no matrix factorization. Compared to covariance estimators for first-order online methods, our estimator for second-order methods is batch-free. We establish the consistency and convergence rate of our estimator, and coupled with asymptotic normality results, we can then perform online statistical inference for the model parameters based on sketched Newton methods. We also discuss the extension of our estimator to constrained problems, and demonstrate its superior performance on regression problems as well as benchmark problems in the CUTEst set. © 2025, CC BY.

关键词： Newton-Raphson method