检索结果-内蒙古大学图书馆

A Surrogate-assisted Multi-objective Grey Wolf Optimizer for Empty-heavy Train Allocation Considering Coordinated Line Utilization Balance

引用

Journal of Bionic Engineering 2025年第1期22卷 383-397页

作者： Zhigang Du Shaoquan Ni Jeng-Shyang Pan Shuchuan Chu School of Transportation and Logistics Southwest Jiaotong UniversityChengdu610031China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031China

This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization *** integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization *** effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective ***,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy *** research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.

关键词： Surrogate-assisted model Grey wolf optimizer Multi-objective optimization Empty-heavy train allocation

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Computation Offloading, Dynamic Pricing and Admission Control in Mobile Edge Computing-Enable Blockchain 24

Joint Optimization of Computation Offloading, Dynamic Pricin...

引用

3rd International Conference on Signal Processing, Computer Networks and Communications, SPCNC 2024

作者： Liu, Yi Zhang, Wenjie Zheng, Yifeng Chen, Liming Key Lab of Data Science and Intelligence Application School of Computer Sciences Minnan Normal University Fujian Zhangzhou China Zhangzhou Affiliated Hospital of Fujian Medical University Fujian Zhangzhou China

ISBN: (纸本)9798400710834

In order to cope with the problem of insufficient resources on mobile devices, the combination of blockchain and Mobile Edge Computing (MEC) has attracted much attention. In this paper, we consider an edge-enabled blockchain system containing two types of miners and a single Edge Service Provider (ESP). Different types of miners have different resource requirements and corresponding prices. Each miner makes a computation offloading decision based on the resource price set by ESP. Different miners possess varying resource requirements and correspond to distinct prices. Miners formulate task offloading decisions based on the prices set by ESP for different resource types. The ESP dynamically adjusts resource price based on miners’ offloading requests and makes admission control according to resource usage in each time slot. The problem is a joint optimization problem of computation offloading, price strategy, and admission control, we model the problem as a sequential decision-making problem and use a dynamic programming algorithm to obtain the optimal solution. Through simulation experiments, our results demonstrate that the proposed algorithm can effectively improve the overall social utility. © 2024 Copyright held by the owner/author(s).

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4595-4609页

作者： Weng, Juanjuan Luo, Zhiming Li, Shaozi Jinan University College of Information Science and Technology Guangzhou510632 China Xiamen University Department of Artificial Intelligence Xiamen361005 China Wuyi University Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Wuyishan354300 China

This paper aims to enhance the transferability of adversarial samples in targeted attacks, where attack success rates remain comparatively low. To achieve this objective, we propose two distinct techniques for improving the targeted transferability from the loss and feature aspects. First, in previous approaches, logit calibrations used in targeted attacks primarily focus on the logit margin between the targeted class and the untargeted classes among samples, neglecting the standard deviation of the logit. In contrast, we introduce a new normalized logit calibration method that jointly considers the logit margin and the standard deviation of logits. This approach effectively calibrates the logits, enhancing the targeted transferability. Second, previous studies have demonstrated that mixing the features of clean samples during optimization can significantly increase transferability. Building upon this, we further investigate a truncated feature mixing method to reduce the impact of the source training model, resulting in additional improvements. The truncated feature is determined by removing the Rank-1 feature associated with the largest singular value decomposed from the high-level convolutional layers of the clean sample. Extensive experiments conducted on the ImageNet-Compatible, CIFAR-10 and ImageNet-1k datasets demonstrate the individual and mutual benefits of our proposed two components, which outperform the state-of-the-art methods by a large margin in black-box targeted attacks. © 2005-2012 IEEE.

关键词： Calibration Closed box Training Standards Translation Perturbation methods Optimization Predictive models Feature extraction Industries

来源：评论

学校读者我要写书评

暂无评论

ControlVideo: conditional control for one-shot text-driven video editing and beyond

引用

science China(Information sciences) 2025年第3期68卷 150-162页

作者： Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML CenterTsinghua Laboratory of Brain and Intelligence Lab Tsinghua University ShengShu Technology Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Pazhou Laboratory (Huangpu)

This paper presents ControlVideo for text-driven video editing — generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions(such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing(e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous studies achieved. The code is available at https://***/thu-ml/controlvideo.

关键词： diffusion models controllable generation text-driven editing video editing long video editing

来源：评论

学校读者我要写书评

暂无评论

Robust adaptive distributed optimization for heterogeneous unknown second-order nonlinear multiagent systems

引用

science China(Information sciences) 2025年第4期68卷 391-392页

作者： Ping GONG Qing-Guo WANG School of Mathematics and Statistics Guangdong University of Foreign Studies Institute of Artificial Intelligence and Future Networks Beijing Normal University Guangdong Provincial/Zhuhai Key Laboratory of Interdisciplinary Research and Application for Data Science Beijing Normal University-Hong Kong Baptist University United International College

The distributed optimization problem has drawn significant attention recently since it has a variety of applications in the economic dispatch of smart grids, regression of distributed data, optimal coordination of mobile robot systems(MRSs),and so on. Different from the traditional leaderless consensus and consensus tracking problems in multiagent systems(MASs), the typical distributed optimization problems are not only required to achieve consensus but also to cooperatively minimize a global cost function [1], where the global cost function is the sum of local cost functions and each local cost function is only known to the agent itself.

关键词：

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Without Forgetting for Vision-Language Models

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年第6期47卷 4489-4504页

作者： Zhou, Da-Wei Zhang, Yuanhan Wang, Yan Ning, Jingyi Ye, Han-Jia Zhan, De-Chuan Liu, Ziwei Nanjing University School of Artificial Intelligence China Nanjing University National Key Laboratory for Novel Software Technology Nanjing210023 China Nanyang Technological University S-Lab College of Computing and Data Science 639798 Singapore

Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual information to grasp core features, recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations with the aid of textual information. However, when continually trained with new classes, VLMs often suffer from catastrophic forgetting of former knowledge. Applying VLMs to CIL poses two major challenges: 1) how to adapt the model without forgetting;and 2) how to make full use of the multi-modal information. To this end, we propose PROjectiOn Fusion (Proof) that enables VLMs to learn without forgetting. To handle the first challenge, we propose training task-specific projections based on the frozen image/text encoders. When facing new tasks, new projections are expanded, and former projections are fixed, alleviating the forgetting of old concepts. For the second challenge, we propose the fusion module to better utilize the cross-modality information. By jointly adjusting visual and textual features, the model can capture better task-specific semantic information that facilitates recognition. Extensive experiments on nine benchmark datasets with various continual learning scenarios and various VLMs validate that Proofachieves state-of-the-art performance. Code is available at https://***/zhoudw-zdw/PROOF. © 1979-2012 IEEE.

关键词： Visualization Tuning Adaptation Models Training Transformers Predictive Models Continuing Education Software Resists Learning Systems Class Incremental Learning Vision Language Model Continual Learning Catastrophic Forgetting Vision Language Models Visual Information Visual Features Benchmark datasets Textual Information Incremental Learning Textual Features Catastrophic Forgetting Recent Advances In Models Fine Tuned Learning Process Contextual Information Latent Space Joint Space Linear Layer Subsequent Task Self Attention Mechanism Training Instances Pre Trained Weights TV Series Projection Layer Image Encoder Unseen Classes Pre Trained Encoder Domain Gap Text Encoder Vision Transformer Tuning Techniques

来源：评论

学校读者我要写书评

暂无评论

Byzantine-robust distributed support vector machine

引用

science China Mathematics 2025年第3期68卷 707-728页

作者： Xiaozhou Wang Weidong Liu Xiaojun Mao School of Statistics East China Normal UniversityShanghai 200062China Key Laboratory of Advanced Theory and Application in Statistics and Data Science(Ministry of Education) East China Normal UniversityShanghai 200062China School of Mathematical Sciences Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Artificial Intelligence(Ministry of Education) Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Scientific and Engineering Computing(Ministry of Education) Shanghai Jiao Tong UniversityShanghai 200240China

The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines may behave abnormally and send arbitrary information to the central machine(known as Byzantine failures), which can invalidate the distributed algorithms based on the assumption of faultless systems. This paper studies Byzantine-robust distributed algorithms for support vector machines(SVMs) in the context of binary classification. Despite a vast literature on Byzantine problems, much less is known about the theoretical properties of Byzantine-robust SVMs due to their unique challenges. In this paper, we propose two distributed gradient descent algorithms for SVMs. The median and trimmed mean operations in aggregation can effectively defend against Byzantine failures. Theoretically, we show the convergence of the proposed estimators and provide the statistical error rates. After a certain number of iterations, our estimators achieve near-optimal rates. Simulation studies and real data analysis are conducted to demonstrate the performance of the proposed Byzantine-robust distributed algorithms.

关键词： Byzantine robustness convergence distributed learning support vector machine

来源：评论

学校读者我要写书评

暂无评论

Dynamic updating approximations of local multigranulation neighborhood covering rough sets

引用

Soft Computing 2025年第6期29卷 2531-2550页

作者： Shi, Qi Zhang, Yan-Lan School of Computer Science Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China

The lower and upper approximations in rough set theory are important for dealing with uncertain knowledge. The covering rough set is an important part of the rough set theory and is suitable for dealing with numerical data. With the development of information technology, the information is constantly updated and changed in various information systems, and it is crucial to efficiently obtain the lower and upper approximations in dynamic environments. In this paper, the matrix-based methods for updating the approximate operators of local multigranulation neighborhood covering rough sets when objects are added or deleted are mainly investigated. Firstly, the local multigranulation neighborhood covering rough set model is introduced. Then, we analyze the relationships between the prior matrices and the updating matrices when objects change. Meanwhile, the dynamic updating processes for lower and upper approximations are proposed. The time complexity analyses of algorithms theoretically prove the efficiency of dynamic algorithms compared with static ones. To illustrate the effectiveness of the proposed dynamic algorithms, six datasets from the UCI are employed for comparative experiments. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Next-POI Recommendation via Spatial-Temporal Knowledge Graph Contrastive Learning and Trajectory Prompt

引用

IEEE Transactions on Knowledge and data Engineering 2025年第6期37卷 3570-3582页

作者： Chen, Wei Huang, Haoyu Zhang, Zhiyu Wang, Tianyi Lin, Youfang Chang, Liang Wan, Huaiyu Guilin University of Electronic Technology Guangxi Key Lab of Trusted Software Guangxi Guilin541004 China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Chinese University of Hong Kong Department of Computer Science and Engineering Ma Liu Shui Hong Kong Beijing Jiaotong University Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Beijing100044 China

Next POI (Point-of-Interest) recommendation aims to forecast users' future movements based on their historical check-in trajectories, holding significant value in location-based services. Existing methods address trajectory data sparsity by integrating rich auxiliary information or using spatial-temporal knowledge graphs (STKGs), showing promising results. Yet, they face two main challenges: i) Due to the difficulty of transforming structured trajectory data into trajectory text describing users' spatial-temporal mobility, the powerful reasoning ability of pre-trained language models is rarely explored to enhance recommendation performance. ii) Methods based on STKG can introduce external knowledge inconsistent with user preferences, leading to the knowledge noise generated hampering the accuracy of recommendations. To this end, we propose a novel approach called STKG-PLM that integrates STKG contrastive learning and prompt pre-trained language model (PLM) to enhance the next POI recommendation. Specifically, we design a spatial-temporal trajectory prompt template that transforms structured trajectories into text corpus based on STKG, serving as the input of PLM to understand the movement pattern of users from coarse-grained and fine-grained perspectives. Additionally, we propose an STKG contrastive learning framework to mitigate the introduced knowledge noise. Extensive experiments on three real-world datasets demonstrate that STKG-PLM exhibits notable performance improvements over the state-of-the-art baseline methods. © 1989-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：