检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Chaoqi Tang, Luyao Huang, Hui College of Computer Science and Software Engineering Shenzhen University China School of Informatics Xiamen University China

Since deep learning models are usually deployed in non-stationary environments, it is imperative to improve their robustness to out-of-distribution (OOD) data. A common approach to mitigate distribution shift is to regularize internal representations or predictors learned from in-distribution (ID) data to be domain invariant. Past studies have primarily learned pairwise invariances, ignoring the intrinsic structure and high-order dependencies of the data. Unlike machines, humans recognize objects by first dividing them into major components and then identifying the topological relation of these components. Motivated by this, we propose Reconstruct and Match (REMA), a general learning framework for object recognition tasks to endow deep models with the capability of capturing the topological homogeneity of objects without human prior knowledge or fine-grained annotations. To identify major components from objects, REMA introduces a selective slot-based reconstruction module to dynamically map dense pixels into a sparse and discrete set of slot vectors in an unsupervised manner. Then, to model high-order dependencies among these components, we propose a hypergraph-based relational reasoning module that models the intricate relations of nodes (slots) with structural constraints. Experiments on standard benchmarks show that REMA outperforms state-of-the-art methods in OOD generalization and test-time adaptation settings. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Segment Routing: Toward Load Balancing with Limited Control Overheads

引用

Big Data Mining and Analytics 2023年第1期6卷 55-71页

作者： Shu Yang Ruiyu Chen Laizhong Cui Xiaolei Chang College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518000China Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518071China

Segment routing has been a novel architecture for traffic engineering in recent ***,segment routing brings control overheads,i.e.,additional packets headers should be *** overheads can greatly reduce the forwarding efficiency for a large network,when segment headers become too *** achieve the best of two targets,we propose the intelligent routing scheme for traffic engineering(IRTE),which can achieve load balancing with limited control *** achieve optimal performance,we first formulate the problem as a mapping problem that maps different flows to key diversion ***,we prove the problem is nondeterministic polynomial(NP)-hard by reducing it to a k-dense subgraph *** solve this problem,we develop an ant colony optimization algorithm as improved ant colony optimization(IACO),which is widely used in network optimization *** also design the load balancing algorithm with diversion routing(LBA-DR),and analyze its theoretical ***,we evaluate the IRTE in different real-world topologies,and the results show that the IRTE outperforms traditional algorithms,e.g.,the maximum bandwidth is 24.6% lower than that of traditional algorithms when evaluating on BellCanada topology.

关键词： traffic engineering segment routing bandwidth load balancing ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Identification of software Bugs by Analyzing Natural Language-Based Requirements Using Optimized Deep Learning Features

引用

computers, Materials & Continua 2024年第3期78卷 4379-4397页

作者： Qazi Mazhar ul Haq Fahim Arif Khursheed Aurangzeb Noor ul Ain Javed Ali Khan Saddaf Rubab Muhammad Shahid Anwar Department of Computer Science and Engineering and International Bachelor’s Program in Informatics Yuan Ze UniversityZhongliTaoyuan320315Taiwan Department of Computer Science National University of PakistanRawalpindiPunjab46000Pakistan Department of Computer Software Engineering MCSNational University of Sciences and TechnologyIslamabad44000Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Department of Computer Science School of PhysicsEngineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates Department of AI and Software Gachon UniversitySeongnam-SI13120South Korea

software project outcomes heavily depend on natural language requirements,often causing diverse interpretations and issues like ambiguities and incomplete or faulty *** are exploring machine learning to predict software bugs,but a more precise and general approach is *** bug prediction is crucial for software evolution and user training,prompting an investigation into deep and ensemble learning ***,these studies are not generalized and efficient when extended to other ***,this paper proposed a hybrid approach combining multiple techniques to explore their effectiveness on bug identification *** methods involved feature selection,which is used to reduce the dimensionality and redundancy of features and select only the relevant ones;transfer learning is used to train and test the model on different datasets to analyze how much of the learning is passed to other datasets,and ensemble method is utilized to explore the increase in performance upon combining multiple classifiers in a *** National Aeronautics and Space Administration(NASA)and four Promise datasets are used in the study,showing an increase in the model’s performance by providing better Area Under the Receiver Operating Characteristic Curve(AUC-ROC)values when different classifiers were *** reveals that using an amalgam of techniques such as those used in this study,feature selection,transfer learning,and ensemble methods prove helpful in optimizing the software bug prediction models and providing high-performing,useful end mode.

关键词： Natural language processing software bug prediction transfer learning ensemble learning feature selection

来源：评论

学校读者我要写书评

暂无评论

FCA-based θ-iceberg core decomposition in graphs

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第2期15卷 1423-1428页

作者： Hao, Fei Xinchang, Khamphaphone Park, Doo-Soon Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an China School of Computer Science Shaanxi Normal University Xi’an710119 China Department of Computer Science and Engineering Soonchunhyang University Asan31538 Korea Republic of Department of Computer Software Engineering Soonchunhyang University Asan31538 Korea Republic of

Complex networking analysis is a powerful technique for understanding both complex networks and big graphs in ubiquitous computing. Particularly, there are several novel metrics, such as k-clique and k-core are proposed in order to study the relative importance of nodes in complex networks. Among of those metrics, k-core analysis is an effective approach for simplifying graphical structure. However, the relation between k and the scale of networks is not explored in most existing literature. Toward this end, this paper formulate a new research problem, θ-Iceberg Core decomposition in graphs, which is able to incorporate a parameter θ (0 © Springer-Verlag GmbH Germany, part of Springer Nature 2017.

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

User story clustering in agile development:a framework and an empirical study

引用

Frontiers of computer science 2023年第6期17卷 43-59页

作者： Bo YANG Xiuyin MA Chunhui WANG Haoran GUO Huai LIU Zhi JIN School of Information Science and Technology Beijing Forestry UniversityBeijing 100083China Engineering Research Center for Forestry Oriented Intelligent Information Processing National Forestry and Grassland AdministrationBeijing 100083China School of Information Science and Technology North China University of TechnologyBeijing 100144China College of Computer Science and Technology Inner Mongolia Normal UniversityHohhot 010020China Department of Computer Science and Software Engineering Swinburne University of TechnologyHawthorn VIC 3122Australia Key Laboratory of High Confidence Software Technologies(Peking University) Ministry of EducationBeijing 100871China Institute of Software School of Computer SciencePeking UniversityBeijing 100871China

Agile development aims at rapidly developing software while embracing the continuous evolution of user requirements along the whole development *** stories are the primary means of requirements collection and elicitation in the agile development.A project can involve a large amount of user stories,which should be clustered into different groups based on their functionality’s similarity for systematic requirements analysis,effective mapping to developed features,and efficient ***,the current user story clustering is mainly conducted in a manual manner,which is time-consuming and subjective to human *** this paper,we propose a novel approach for clustering the user stories automatically on the basis of natural language ***,the sentence patterns of each component in a user story are first analysed and determined such that the critical structure in the representative tasks can be automatically extracted based on the user story *** similarity of user stories is calculated,which can be used to generate the connected graph as the basis of automatic user story *** evaluate the approach based on thirteen datasets,compared against ten baseline *** results show that our clustering approach has higher accuracy,recall rate and F1-score than these *** is demonstrated that the proposed approach can significantly improve the efficacy of user story clustering and thus enhance the overall performance of agile *** study also highlights promising research directions for more accurate requirements elicitation.

关键词： user story agile development user story mapping clustering

来源：评论

学校读者我要写书评

暂无评论

GATBind: Accurate protein-RNA binding sites prediction via graph attention networks with pre-trained language model

GATBind: Accurate protein-RNA binding sites prediction via g...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Shen, Siyuan Wu, Shangqian Chen, Jie Huang, Zhijian Deng, Lei Central South University School of Computer Science and Engineering Changsha China Xinjiang University School of Software Urumqi China

ISBN: (纸本)9798350386226

Protein-RNA interactions play a pivotal role in various biological processes, making them essential for discovering novel therapeutic targets. Understanding these interactions is crucial for identifying potential drug targets and designing effective therapeutics. However, traditional experimental approaches are costly and time-consuming, highlighting the need for accurate and efficient computational methods to predict RNA-binding sites. In this study, we propose a novel method called GATBind, designed to predict RNA-binding sites on proteins. GATBind introduces a local environment-aware module that captures the local structural information surrounding target residues. Additionally, we incorporate sequence and structural features, including PSSM, HMM, DSSP, and sequence embeddings generated by the pre-trained protein language model ESMFold-2. These features are integrated and processed through a Graph Attention Network (GAT) module to predict RNA-binding sites accurately. Experimental results demonstrate that GATBind outperforms existing state-of-the-art methods, and case studies further validate its effectiveness in predicting RNA-binding sites. © 2024 IEEE.

关键词： Binding sites

来源：评论

学校读者我要写书评

暂无评论

Bridging Fourier and Spatial-Spectral Domains for Hyperspectral Image Denoising 24

Bridging Fourier and Spatial-Spectral Domains for Hyperspect...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Xiao, Jiahua Liu, Yang Zhang, Shizhou Wei, Xing School of Software Engineering Xi'an Jiaotong University Xi'an China School of Computer Science and Engineering Northwest Polytechnical University Xi'an China

ISBN: (纸本)9798400706868

Remarkable progresses have been made in hyperspectral image (HSI) denoising. However, the majority of existing methods are predominantly confined to the spatial-spectral domain, overlooking the untapped potential inherent in the Fourier domain. This paper presents a novel approach to address HSI denoising by bridging the information from the Fourier and spatial-spectral domains. Our method highlights key insights into the Fourier properties within spatial and spectral domains through the Fourier transform. Specifically, we note that the amplitude inherently embody noise and photon reflection characteristics, while the phase holds structural information. These insights unveil new perspectives on the physical properties of HSIs, motivating us to leverage complementary information exchange between Fourier and spatial-spectral domains. To this end, we introduce the Fourier-prior Integration Denoising Network (FIDNet), a potent yet straightforward approach that utilizes Fourier insights to synergistically interact with spatial-spectral domains for superior HSI denoising. In FIDNet, we independently extract spatial and Fourier features through dual branches and merge these representations to enhance spectral evolution modeling through the inherent structure consistency constraints and continuing reflection variation revealed in Fourier prior. Our proposed method demonstrates robust generalization across synthetic and real-world benchmark datasets, achieves comparable results with state-of-the-art methods in both quantitative quality and visual results. The code is available at https://***/MIV-XJTU/FIDNet. © 2024 ACM.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Overlapping Community Guided Hierarchical Self-Attention Pooling 5

Fuzzy Overlapping Community Guided Hierarchical Self-Attenti...

引用

5th International Conference on Intelligent Computing and Human-computer Interaction, ICHCI 2024

作者： Liu, Xin Xiao, Yao Zhang, Zuping School of Computer Science and Engineering Central South University Changsha China School of Software Xinjiang University Urumqi China

ISBN: (纸本)9798350368284

Graph pooling aims at extracting vital information for graph coarsening, and thus helping graph neural networks to improve their graph representation ability. However, existing methods either compress similar nodes by a clustering algorithm or discard unimportant nodes by an importance score, resulting in the coarsened graph suffering from different issues. Therefore, aiming at the goal of breaking through their limitation, this paper develops a fuzzy overlapping community guided hierarchical self-Attention pooling, namely FOCoHSAP. FOCoHSAP performs node selection within every detected community rather than the entire graph, which allows for an explicit preservation of both topology hierarchy and detailed node information. Especially, FOCoHSAP introduces fuzzy overlapping community detection algorithm to explore those fine-grained relationships between nodes and communities, allowing for a more promising learning of graph representation that can be utilized for accurate graph classification. © 2024 IEEE.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Major Depressive Disorder Based on Anomaly Detection with sMRI Gray Matter Slices 10

Diagnosis of Major Depressive Disorder Based on Anomaly Dete...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Xiao, Yao Liu, Xin Qian, Yurong Huang, Bo Tang, Panrui Zhang, Zuping Xinjiang University School of Software Urumqi China Central South University School of Computer Science and Engineering Changsha China

ISBN: (纸本)9798331520861

The current research focus on Major Depressive Disorder (MDD) is a reflection of its significant adverse impact on individuals and society. Structural magnetic resonance imaging (SMRI) is a valuable tool for clinicians in diagnosing and identifying MDD. sMRI employs a uniform imaging protocol, and images of gray matter slices in the same plane across different sMRIs demonstrate high similarity, revealing repetitive anatomical structures between patients. Given the consistency of anatomical structures, the same regional evidence in normal images presents similar physiological structural information. Lesions, meanwhile, cause structural changes that manifest as abnormal patterns. In this paper, we apply the SQUID model, which is capable of detecting abnormal structural information, to the MDD classification problem. The study employed gray matter slice data generated by SMRI from 1025 individuals with MDD and 1205 Healthy Controls(HC). The objective was to undertake an abnormality detection classification task in MDD and HC, and to further verify the pivotal role of the hippocampus in the diagnosis of MDD through masked experiment. The findings contribute novel methods and evidence for the clinical diagnosis of MDD. © 2024 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

ADiffGDA: Exploring Gene-Drug Associations via Adaptive Graph Diffusion Networks

ADiffGDA: Exploring Gene-Drug Associations via Adaptive Grap...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Che Fan, Yanhao Hu, Xiaowen Qian, Yurong Deng, Lei Xinjiang University School of Software Urumqi China Central South University School of Computer Science and Engineering Changsha China

ISBN: (纸本)9798350386226

Exploring gene-drug associations is a key step in identifying new drug candidates, but traditional experimental methods are often expensive and time-consuming. While Graph Neural Network (GNN)-based models have demonstrated effectiveness in association prediction tasks, they face challenges in the information aggregation process. Existing GNN models either treat all nodes uniformly or rely on simple attention mechanisms to assign weights to neighboring nodes, limiting their capacity to capture complex relationships and improve performance. To address these limitations, we propose a novel adaptive graph diffusion network, ADiffGDA, for gene-drug association prediction. The model begins by randomly initializing embeddings for genes and drugs, which are then updated through neighborhood information aggregation. A key feature of ADiffGDA is the incorporation of a heat kernel, enabling each node to dynamically adjust aggregation weights based on its local structure. This approach allows the model to better capture variations in node types and local neighborhood patterns. Through extensive comparative experiments, we show that ADiffGDA outperforms existing state-of-the-art methods. Furthermore, case studies validate its effectiveness as a predictive tool, offering valuable insights for future biological experiments. The code and datasets for ADiffGDA are freely available at https://***/one-melon/ADiffGDA. © 2024 IEEE.

关键词： Graph neural networks

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：