检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yiheng Wu, Shaowu Xu, Yuanzhuo Wu, Jiajun Xu, Shang Drew, Steve Niu, Xiaoguang School of Computer Science Wuhan University China Department of Electrical and Software Engineering University of Calgary Canada Department of Computer Science University College London United Kingdom

ISBN: (纸本)157735897X

Adaptive optimizers such as Adam and RMSProp have gained attraction in complex neural networks, including generative adversarial networks (GANs) and Transformers, thanks to their stable performance and fast convergence compared to non-adaptive optimizers. A frequently overlooked limitation of adaptive optimizers is that adjusting the learning rate of each dimension individually would ignore the knowledge of the whole loss landscape, resulting in slow updates of parameters, invalidating the learning rate adjustment strategy and eventually leading to widespread insufficient convergence of parameters. In this paper, we propose HVAdam, a novel optimizer that associates all dimensions of the parameters to find a new parameter update direction, leading to a refined parameter update strategy for an increased convergence rate. We validated HVAdam in extensive experiments, showing its faster convergence, higher accuracy, and more stable performance on image classification, image generation, and natural language processing tasks. Particularly, HVAdam achieves a significant improvement on GANs compared with other state-of-the-art methods, especially in Wasserstein-GAN (WGAN) and its improved version with gradient penalty (WGAN-GP). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Topic Interpretability for Neural Topic Modeling Through Topic-Wise Contrastive Learning

Enhancing Topic Interpretability for Neural Topic Modeling T...

引用

International Conference on Data engineering

作者： Xin Gao Yang Lin Ruiqing Li Yasha Wang Xu Chu Xinyu Ma Hailong Yu Software Engineering Institution School of Computer Science Peking University Beijing China Key Lab of High Confidence Software Technologies Ministry of Education Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China Center on Frontiers of Computing Studies School of Computer Science Peking University

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Data mining and knowledge discovery are essential aspects of extracting valuable insights from vast datasets. Neural topic models (NTMs) have emerged as a valuable unsupervised tool in this field. However, the predominant objective in NTMs, which aims to discover topics maximizing data likelihood, often lacks alignment with the central goals of data mining and knowledge discovery which is to reveal interpretable insights from large data repositories. Overemphasizing likelihood maximization without incorporating topic regularization can lead to an overly expansive latent space for topic modeling. In this paper, we present an innovative approach to NTMs that addresses this misalignment by introducing contrastive learning measures to assess topic interpretability. We propose a novel NTM framework, named ContraTopic, that integrates a differentiable regularizer capable of evaluating multiple facets of topic interpretability throughout the training process. Our regularizer adopts a unique topic-wise contrastive methodology, fostering both internal coherence within topics and clear external distinctions among them. Comprehensive experiments conducted on three diverse datasets demonstrate that our approach consistently produces topics with superior interpretability compared to state-of-the-art NTMs.

关键词： Training Measurement Contrastive learning Coherence Knowledge discovery Data engineering Data models

来源：评论

学校读者我要写书评

暂无评论

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories 62

DevEval: A Manually-Annotated Code Generation Benchmark Alig...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Li, Jia Li, Ge Zhao, Yunfei Li, Yongmin Liu, Huanyu Zhu, Hao Wang, Lecheng Liu, Kaibo Fang, Zheng Wang, Lanshen Ding, Jiazheng Zhang, Xuanming Zhu, Yuqi Dong, Yihong Jin, Zhi Li, Binhua Huang, Fei Li, Yongbin Gu, Bin Yang, Mengfei School of Computer Science Peking University China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education China Alibaba Group China Beijing Institute of Control Engineering China China Academy of Space Technology China

ISBN: (纸本)9798891760998

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. To address the knowledge gap, we propose a new benchmark named DevEval, which has three advances. 1 DevEval aligns with real-world repositories in multiple dimensions, e.g., code and dependency distributions. 2 DevEval is annotated by 13 developers and contains comprehensive annotations (e.g., requirements, original repositories, reference code, and reference dependencies). 3 DevEval comprises 1,825 testing samples from 115 repositories, covering 10 popular domains (e.g., Internet, Database). Based on DevEval, we propose repository-level code generation and evaluate 8 popular LLMs on DevEval (e.g., gpt-4, gpt-3.5, StarCoder 2, DeepSeek Coder, CodeLLaMa). Our experiments reveal these LLMs' coding abilities in real-world code repositories. For example, the highest Pass@1 of gpt-4 only is 53.04% in our experiments. We also analyze LLMs' failed cases and summarize their shortcomings. We hope DevEval can facilitate the development of LLMs in real code repositories. DevEval, prompts, and LLMs' predictions have been released. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Moving Target Defense for Multicast in software-Defined Satellite Networks

Deep Reinforcement Learning-Based Moving Target Defense for ...

引用

IEEE International Conference on Communications (ICC)

作者： Yibo Lian Tao Zhang Changqiao Xu Wei Dong Minrui Xu Zhenyu Xiahou Jiawen Kang Jiqiang Liu Dusit Niyato School of Computer Science Beijing University of Posts and Telecommunications School of Software Engineering Beijing Jiaotong University School of Computer Science and Engineering Nanyang Technological University Jiangxi Academy of Cyber Security School of Automation Guangdong University of Technology

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The development of LEO satellite networks (LSN) makes them a potential solution to deliver broadcast/multicast traffic to deploy and upgrade massive amounts of Internet of Things (IoT) devices in future 6G networks. However, inherent resource constraints of LSN leave them vulnerable to a multitude of security threats, most notably distributed denial-of-service (DDoS) attacks. Existing solutions are primarily based on machine learning detection methods which are incapable of defending against unknown zero-day attacks. This paper presents an innovative solution leveraging deep reinforcement learning (DRL) to create a dynamic multicast tree based on moving target defense (MTD), aimed at enhancing the security of multicast services in LSN. The proposed solution adopts an adaptive orbital tree mutation (AOTM) scheme that dynamically adjusts multicast tree configurations considering quality of service (QoS) constraints to avoid attacks on vulnerable nodes. Simulations demonstrate the effectiveness of the AOTM scheme, showcasing its superior defense success rates compared to existing state-of-the-art algorithms.

关键词： Space vehicles Multicast algorithms Satellites Heuristic algorithms Satellite broadcasting software algorithms Quality of service

来源：评论

学校读者我要写书评

暂无评论

PointDKT: Dual-Key Transformer for Point Cloud

PointDKT: Dual-Key Transformer for Point Cloud

引用

International Symposium on Autonomous Systems (ISAS)

作者： Jifeng Yang Guang-Guan Zhou Yang Chen School of Software Southeast University Nanjing China School of Biological Science and Medical Engineering Southeast University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

ISBN: (数字)9798350363173

ISBN: (纸本)9798350363180

Benefiting from the development of transformer-based networks in natural language processing and computer vision, researches on 3D point cloud understanding have made great progress in recent years. However, existing works often focus solely on aggregating local features or construct global dependencies through methods that significantly increase memory and computation complexity. Addressing these challenges, we present Point Dual-Key Transformer(PDKT), a novel and straightforward end-to-end network architecture. To expand the receptive fields and preserve the local geometric structural information, we introduce an efficient dual-key cross attention mechanism, which builds upon standard cross attention to facilitate global feature capture across the network without neglecting local detail. Furthermore, we adopt a learnable operator to automatically integrate local and global branches. Extensive experiment results demonstrate the effectiveness and superiority of our method on point cloud understanding tasks

关键词： Point cloud compression computer vision Three-dimensional displays computer architecture Network architecture Transformers Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Ensemble Distillation for Out-of-distribution Detection 29

Ensemble Distillation for Out-of-distribution Detection

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Wang, Dongdong Xu, Jingyao Lu, Siyang Wei, Xiang Wang, Liqiang University of Central Florida Department of Civil Environmental and Construction Engineering OrlandoFL United States Beijing Jiaotong University School of Computer and Information Technolog Beijing China Beijing Jiaotong University School of Software Engineering Beijing China University of Central Florida Department of Computer Science OrlandoFL United States

ISBN: (纸本)9798350330717

Out-of-distribution detection is critical to a reliable application of deep neural networks. To reduce model uncertainty, we propose a simple yet effective approach of ensemble knowledge distillation. We blend ensemble model and knowledge distillation to improve model generalization on indomain recognition, thereby yielding accurate and robust out-of-distribution detection. The former effectively expands data recognition feature space, while the latter further regularizes the model through knowledge distillation, enhancing in-domain feature recognition. This effective integration successfully yields lower model uncertainty on in-domain feature recognition and improves anomaly detection in a more scalable manner. We justify our approach through extensive experiments on various benchmarks, demonstrating its significant improvement in out- of-distribution detection. We validate our approach with a variety of up-to-date DNNs, like Vision Transformer. © 2023 IEEE.

关键词： Data Augmentation Ensemble Learning Knowledge Distillation Out-of-distribution Detection

来源：评论

学校读者我要写书评

暂无评论

A Study on the Construction and Practical Application of the Smart Education Data Platform at Guizhou Traffic Technician and Transportation College 14

A Study on the Construction and Practical Application of the...

引用

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Li, Hong Zhang, Hong Deng, Shaoxun Li, Bo Guizhou Bit Software Co. Ltd. Research and Development Department Guiyang China Guizhou Traffic Technician and Transportation College Department of Management Engineering Guiyang China Guizhou University School of Computer Science and Technology Guiyang China

ISBN: (纸本)9798350356670

This paper investigates the digital transformation at Guizhou Traffic Technician and Transportation College, aligned with the 'China Education Modernization 2035' agenda. It introduces a microservices-based data platform aimed at upgrading educational IT systems, enhancing instructional quality, and informing decisions through smarter data use. The approach integrates microservices, cloud, big data, and AI to achieve efficient data handling and analytics, leading to improved management and decision-making processes. The study documents the platform's architecture, security, challenges, and solutions, along with successes like data visualization and automated reporting. Findings emphasize the project's relevance for vocational education's digital transition, pointing out future challenges, including data security and technology updates. The research concludes with key takeaways for institutions undergoing digitalization, underscoring the paramountcy of data security and tech optimization. © 2024 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Fast Mesh Reconstruction from Single View Based on GCN and Topology Modification

引用

computer Systems science & engineering 2023年第5期45卷 1695-1709页

作者： Xiaorui Zhang Feng Xu Wei Sun Yan Jiang Yi Cao Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China Department of Electrical and Computer Engineering University of WindsorWindsorONN9B 3P4Canada

3D reconstruction based on single view aims to reconstruct the entire 3D shape of an object from one *** existing methods reconstruct the mesh surface of complex objects,the surface details are difficult to predict and the reconstruction visual effect is poor because the mesh representation is not easily integrated into the deep learning framework;the 3D topology is easily limited by predefined templates and inflexible,and unnecessary mesh self-intersections and connections will be generated when reconstructing complex topology,thus destroying the surface details;the training of the reconstruction network is limited by the large amount of information attached to the mesh vertices,and the training time of the reconstructed network is too *** this paper,we propose a method for fast mesh reconstruction from single view based on Graph Convolutional Network(GCN)and topology *** use GCN to ensure the generation of high-quality mesh surfaces and use topology modification to improve the flexibility of the ***,a feature fusion method is proposed to make full use of the features of each stage of the image *** use 3D open dataset ShapeNet to train our network and add a new weight parameter to speed up the training *** experiments demonstrate that our method can not only reconstruct object meshes on complex topological surfaces,but also has better qualitative and quantitative results.

关键词： 3D surface reconstruction deep learning GCN topology modification end-to-end framework

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Privacy in Real-Time Trajectory Releases for AI-Driven Consumer Applications

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Cai, Sujin Tian, Wei Lv, Taizhi Wang, Xiangchen Li, Xin Jiangsu Maritime Institute School of Information and Engineering Nanjing211106 China Guizhou University of Commerce College of Computer and Information engineering Guiyang550014 China Southern University of Science and Technology College of Computer Science Shenzhen518055 China Hohai University College of Computer Science and Software Engineering Nanjing211106 China

Intelligent consumer applications optimize product recommendations by analyzing users' real-time trajectory information and mobility patterns to gain insights into their consumption preferences. However, privacy concerns often cause individuals to hesitate when sharing their locations. This paper introduces a real-time trajectory release scheme called Dynamic Trajectory Releasing based on Geo-indistinguishability (DTRG) that ensures client-side data protection. A significant contribution of this work is the introduction of a novel concept, w-event Geo-indistinguishability, which extends the measurement of privacy for real-time trajectories. Building upon the theoretical foundation of w-event Geo-indistinguishability, we design a dynamic privacy budget allocation strategy that doesn't require pre-setting trajectory length. This strategy recycles unused privacy budgets and progressively reallocating them in a backward cumulative manner, enhancing the utilization efficiency of the privacy budget. By incorporating users' travel information for prediction, DTRG adaptively perturbs real locations based on prediction results. Through the collaborative operation of the Prediction Mechanism (PM), Detection Mechanism (DM) and Noisy Mechanism (NM), this approach further optimizes the utility of the budget. Experimental results demonstrate that DTRG significantly improves data availability, achieving up to a 36% increase compared to some competing algorithms while maintaining the desired level of privacy. © 1975-2011 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art Approach: Boosting IoT Sensor Network Security with Visual Secret Sharing

State-of-the-Art Approach: Boosting IoT Sensor Network Secur...

引用

Smart World Congress (SWC), IEEE

作者： Sijjad Ali Jia Wang Victor Chung Ming Leung Uzair Aslam Bhatti Mughair Aslam Bhatti College of Computer Science and Software Engineering Shenzhen University Guangdong China School of Information and Communication Engineering Hainan University China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

This research paper is based on the issue of protecting the sensor networks in the era of IoT because the data is very sensitive and huge, and is collected in resource-constrained environments. We put forward a new approach to the enhancement of the security of IoT sensor networks by applying VSS on visual data. Our approach is based on the implementation of the VSS approach which implies that no single node will contain full information about the visual input which will be divided among the nodes. Furthermore, this approach also increases the security of the data, and at the same time is appropriate for the IoT environments since it does not require a large amount of computational power and network bandwidth. In addition, we explain how this method can be used, discuss its features, and based on the data from the experiments, prove the effectiveness of the suggested approach. The results of the research show that data security and the ability to counteract attacks can be resist if VSS is used in systems of IoT sensor networks.

关键词： Visualization Resists Bandwidth Network security Boosting Internet of Things Cryptography

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：