检索结果-内蒙古大学图书馆

2nd Asia Conference on Advanced Robotics, Automation, and Control Engineering, ARACE 2023

作者： Shen, Qinghua Liu, Guiquan University of Science and Technology of China School of Data Science Hefei China University of Science and Technology of China School of Computer Science and Technology Hefei China

ISBN: (纸本)9798350328363

Neural networks excel at mining the static graph, but how to learn from streaming graphs without forgetting previous knowledge is an emerging challenge and well known as continual graph learning (CGL). Despite recent progress in this area, two significant challenges persist: 1) most of existing works only manipulate on the intermediate graph embedding and ignore intrinsic properties of graphs, which limits the learning method's pertinence. 2) recent attempts obscure the transferable knowledge and lack explicit description for the transfer process. It is non-trivial to tell what and how the information is transferred across graphs. In this paper, we point out that latent relations behind graph edges, as an intrinsic graph property, can be attributed as an invariant factor for the evolving graph sequence and lead a possible knowledge transfer. Motivated by this, we design a relation-aware adaptive model, dubbed as RAM-CG, which consists of a relation analysis module to explore latent relations behind edges for message-passing and a task-awareness masking classifier to account for the shifting knowledge in the graph sequence. Extensive experiments show that RAM-CG provides significant 2.2%, 4.2% and 6.6% accuracy improvements over the state-of-the-art results on CitationNet, OGBN-arxiv and TWITCH dataset. © 2023 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

ALRS: An Attention Loss Function based on Row-Sparsity for Incremental Learning 8

ALRS: An Attention Loss Function based on Row-Sparsity for I...

引用

8th International Conference on computer and Communication Systems, ICCCS 2023

作者： Xia, Yingying Lu, Bo Ji, Jianmin School of Data Science University of Science and Technology of China Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9781665456128

Incremental learning has received significant attention, but the problem of catastrophic forgetting remains a major challenge for existing approaches. This issue hinders models from accumulating knowledge over long stretches. To address this problem, we propose a new approach called Attention Loss function based on Row-Sparsity (ALRS) that mines significant patches by simultaneously learning patch weights and logits (class vectors) using the same parameters. We integrate the attention mechanism with the novel loss function to avoid catastrophic forgetting. This innovative approach enables the model to conflate the newly introduced classes with the existing ones, without the need to store any data or models from the previous steps' base classes. To assess its efficacy, we incorporate ALRS into the distillation loss for validation and conduct a thorough evaluation of the approach's performance on three datasets: CIFAR-100, Caltech-101, and CUBS-200-2011. Compared to LWM, which also does not store data, our method achieves an average improvement of more than 8 percentage points with an absolute advantage on CIFAR-100. Additionally, on Caltech-101 and CUBS-200-2011, our new approach provides comparable accuracy to baseline. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Probe Machine Based Computing Model for Maximum Clique Problem

引用

Chinese Journal of Electronics 2022年第2期31卷 304-312页

作者： CUI Jianzhong YIN Zhixiang TANG Zhen YANG Jing Department of Computer Huainan Union University School of Electronic and Information Engineering Anhui University of Science & Technology School of Mathematics Physics and Statistics Shanghai University of Engineering Science School of Mathematics and Big Data Anhui University of Science & Technology

Probe machine(PM) is a recently reported mathematic model with massive parallelism. Herein,we presented searching the maximum clique of an undirected graph with six vertices. We constructed data library containing n sublibraries, each sublibrary corresponded to a vertex in the given graph. Then, probe library according to the induced subgraph was designed in order to search and generate all maximal cliques. Subsequently,we performed probe operation, and all maximal cliques were generated in parallel. The advantages of the proposed model lie in two aspects. On one hand, solution to NP-complete problem is generated in just one step of probe operation rather than found in vast solution *** the other hand, the proposed model is highly *** work demonstrates that PM is superior to TM in terms of searching capacity when tackling NP-complete problem.

关键词： maximal cliques maximum clique problem searching capacity data library NP-complete problem computational complexity model lie induced subgraph probe operation undirected graph mathematic model graph theory parallel algorithms optimisation parallelism computing model vertex probe library probe machine

来源：评论

学校读者我要写书评

暂无评论

K-Means Clustering with Local Distance Privacy

引用

Big data Mining and Analytics 2023年第4期6卷 433-442页

作者： Mengmeng Yang Longxia Huang Chenghua Tang the Data61 Commonwealth Scientific and Industrial Research OrganizationMelbourne 3168Australia the School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212013China. the School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin 541010China

With the development of information technology,a mass of data are generated every *** and analysing these data help service providers improve their services and gain an advantage in the fierce market competition.K-means clustering has been widely used for cluster analysis in real ***,these analyses are based on users’data,which disclose users’*** differential privacy has attracted lots of attention recently due to its strong privacy guarantee and has been applied for clustering ***,existing K-means clustering methods with local differential privacy protection cannot get an ideal clustering result due to the large amount of noise introduced to the whole dataset to ensure the privacy *** solve this problem,we propose a novel method that provides local distance privacy for users who participate in the clustering *** of making the users’records in-distinguish from each other in high-dimensional space,we map the user’s record into a one-dimensional distance space and make the records in such a distance space not be distinguished from each *** be specific,we generate a noisy distance first and then synthesize the high-dimensional data *** propose a Bounded Laplace Method(BLM)and a Cluster Indistinguishable Method(CIM)to sample such a noisy distance,which satisfies the local differential privacy guarantee and local dE-privacy guarantee,***,we introduce a way to generate synthetic data records in high-dimensional *** experimental evaluation results show that our methods outperform the traditional methods significantly.

关键词： K-means clustering local differential privacy data analysis

来源：评论

学校读者我要写书评

暂无评论

A Novelty Framework in Image-Captioning with Visual Attention-Based Refined Visual Features

引用

computers, Materials & Continua 2025年第3期82卷 3943-3964页

作者： Alaa Thobhani Beiji Zou Xiaoyan Kui Amr Abdussalam Muhammad Asim Mohammed ELAffendi Sajid Shah School of Computer Science and Engineering Central South UniversityChangsha410083China Electronic Engineering and Information ScienceDepartment University of Science and Technology of ChinaHefei230026China EIAS Data Science Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

Image captioning,the task of generating descriptive sentences for images,has advanced significantly with the integration of semantic ***,traditional models still rely on static visual features that do not evolve with the changing linguistic context,which can hinder the ability to form meaningful connections between the image and the generated *** limitation often leads to captions that are less accurate or *** this paper,we propose a novel approach to enhance image captioning by introducing dynamic interactions where visual features continuously adapt to the evolving linguistic *** model strengthens the alignment between visual and linguistic elements,resulting in more coherent and contextually appropriate ***,we introduce two innovative modules:the Visual Weighting Module(VWM)and the Enhanced Features Attention Module(EFAM).The VWM adjusts visual features using partial attention,enabling dynamic reweighting of the visual inputs,while the EFAM further refines these features to improve their relevance to the generated *** continuously adjusting visual features in response to the linguistic context,our model bridges the gap between static visual features and dynamic language *** demonstrate the effectiveness of our approach through experiments on the MS-COCO dataset,where our method outperforms state-of-the-art techniques in terms of caption quality and contextual *** results show that dynamic visual-linguistic alignment significantly enhances image captioning performance.

关键词： Image-captioning visual attention deep learning visual features

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Model Counting 36

A Machine Learning Approach to Model Counting

引用

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Dalla, Marco Visentin, Andrea O'Sullivan, Barry SFI Centre for Research Training in AI School of Computer Science & IT University College Cork Ireland Insight Centre for Data Analytics School of Computer Science & IT University College Cork Ireland

ISBN: (纸本)9798331527235

Model counting (#SAT) is the problem of computing the number of satisfying assignments for a given Boolean formula. It has a significant theoretical and practical interest. Tackling it can be challenging since the number of potential solution grows exponentially with the number of variables. Due to the inherent complexity of the problem, approaches to approximate model counting have been developed as a practical alternative. These methods extract the number of solutions within user-specified tolerance and confidence levels and in a fraction of the time required by exact model counters. However, even these methods require extensive computations, restricting their applicability to relatively small instances. In this paper, we propose a new approximate machine learning model counter that overcome this limitation. Predicting the number of solutions can be seen as a regression problem. We deploy an array of machine learning techniques trained to infer the approximate number of solutions based on statistical features extracted from a SAT propositional formula. Extensive numerical experiments performed on synthetic crafted and benchmark datasets show that learning approaches can provide a good approximation of the number of solutions with a much lower computational time and resource cost than the state-of-the-art approximate and exact model counters, making it possible to approximate the model count of instances previously out of reach. We then investigated the structural factors that lead to a high model count using AI explainability approaches. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Concise and Varied Visual Features-Based Image Captioning Model with Visual Selection

引用

computers, Materials & Continua 2024年第11期81卷 2873-2894页

作者： Alaa Thobhani Beiji Zou Xiaoyan Kui Amr Abdussalam Muhammad Asim Naveed Ahmed Mohammed Ali Alshara School of Computer Science and Engineering Central South UniversityChangsha410083China Electronic Engineering and Information Science Department University of Science and Technology of ChinaHefei230026China EIAS Data Science Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic UniversityRiyadh11432Saudi Arabia

Image captioning has gained increasing attention in recent *** characteristics found in input images play a crucial role in generating high-quality *** studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption ***,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these ***,this leads to enhanced captioning network *** light of this,we present an image captioning framework that efficiently exploits the extracted representations of the *** framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language *** VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features ***,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative *** the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s *** the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve *** implementation code can be found here:https://***/althobhani/VFDICM(accessed on 30 July 2024).

关键词： Visual attention image captioning visual feature detector visual feature visual attention

来源：评论

学校读者我要写书评

暂无评论

Media Power Measuring via Emotional Contagion

引用

Journal of Social Computing 2024年第1期5卷 15-35页

作者： Xue Lin Hong Huang Zongya Li Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China School of Journalism Huazhong University of Science and TechnologyWuhan 430074China

Media power,the impact that media have on public opinion and perspectives,plays a significant role in maintaining internal stability,exerting external influence,and shaping international dynamics for nations/***,prior research has primarily concentrated on news content and reporting time,resulting in limitations in evaluating media *** more accurately assess media power,we use news content,news reporting time,and news emotion simultaneously to explore the emotional contagion between *** use emotional contagion to measure the mutual influence between media and regard the media with greater impact as having stronger media *** propose a framework called Measuring Media Power via Emotional Contagion(MMPEC)to capture emotional contagion among media,enabling a more accurate assessment of media power at the media and national/regional *** also interprets experimental results through correlation and causality analyses,ensuring *** analyses confirm the higher accuracy of MMPEC compared to other baseline models,as demonstrated in the context of COVID-19-related news,yielding compelling and interesting insights.

关键词： explainability media power emotional contagion

来源：评论

学校读者我要写书评

暂无评论

Explore Statistical Properties of Undirected Unweighted Networks from Ensemble Models 27th

Explore Statistical Properties of Undirected Unweighted Netw...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Xunda Wu, Xing Wang, Jianjia School of Computer Engineering and Science Shanghai University Shanghai China Engineering and Science Shanghai Institute for Advanced Communication and Data Science School of Computer Shanghai University Shanghai China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou China

ISBN: (纸本)9783031783975

Complex network theory has been widely demonstrated as a powerful tool in modeling and characterizing various complex systems. In the past, complex network theory has focused on the behaviors as well as the characteristics of the network nodes and edges. However, with the continuous evolution of society, traditional graph theory faces challenges due to the emergence of extermely large network structures. Recently, complex network method based statistics has attracted much attention. The new approach effectively manages very large networks and uncovers their intrinsic properties. In this paper, we present a complex network analysis model for undirected, unweighted networks based on a statistical analysis approach. This model is inspired by the ensemble model in thermostatistical physics. Based on the established mathematical model, we derive physical measures that reflect the intrinsic properties of the network, including Entropy, Free Energy, Temperature, and so on. In the experimental part, we first explored the mathematical characterization of these metrics. Then, we observed the performance of various network categories under the same metric. Finally, we applied these measures to the field of graph classification. Extensive experiments demonstrate the effectiveness and superiority of the proposed method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference

An Empirical Study on Cross-lingual Vocabulary Adaptation fo...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Yamaguchi, Atsuki Villavicencio, Aline Aletras, Nikolaos School of Computer Science University of Sheffield United Kingdom Department of Computer Science Institute of Data Science and Artificial Intelligence University of Exeter United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9798891761681

The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent studies have shown that their inference efficiency deteriorates when generating text in languages other than English. This results in increased inference time and costs. Cross-lingual vocabulary adaptation (CVA) methods have been proposed for adapting models to a target language aiming to improve downstream performance. However, the effectiveness of these methods on increasing inference efficiency of generative LLMs has yet to be explored. In this paper, we perform an empirical study of five CVA methods on four generative LLMs (including monolingual and multilingual models) across four typologically-diverse languages and four natural language understanding tasks. We find that CVA substantially contributes to LLM inference speedups of up to 271.5%. We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models. © 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

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：