检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Zhenglin Wu, Jialong Lai, Yilong Zhang, Congzhi Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by encouraging the exploration of intermediate steps, surpassing the capabilities of chain-of-thought prompting. However, significant inference latency is introduced due to the systematic exploration and evaluation of multiple thought paths. This paper introduces SEED, a novel and efficient inference framework to improve both runtime speed and GPU memory management concurrently. Based on a scheduled speculative execution, SEED efficiently handles multiple iterations for thought generation and state evaluation, leveraging a rounds-scheduled strategy to manage draft model dispatching. Extensive experimental evaluations on three reasoning datasets demonstrate the superior speedup performance of SEED. © 2025 Association for Computational Linguistics.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

Calibration Bottleneck: Over-compressed Representations are Less Calibratable 41

Calibration Bottleneck: Over-compressed Representations are ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Deng-Bao Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Lab. of Computer Network and Information Integration Southeast University MOE China

Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a model is to be well recalibrated post-hoc. We find that the widely used weight decay regularizer detrimentally affects model calibratability, subsequently leading to a decline in final calibration performance after post-hoc calibration. To identify the underlying causes leading to poor calibratability, we delve into the calibratability of intermediate features across the hidden layers. We observe a U-shaped trend in the calibratability of intermediate features from the bottom to the top layers, which indicates that over-compression of the top representation layers significantly hinders model calibratability. Based on the observations, this paper introduces a weak classifier hypothesis, i.e., given a weak classification head that has not been over-trained, the representation module can be better learned to produce more calibratable features. Consequently, we propose a progressively layer-peeled training (PLP) method to exploit this hypothesis, thereby enhancing model calibratability. Our comparative experiments show the effectiveness of our method, which improves model calibration and also yields competitive predictive performance. Copyright 2024 by the author(s)

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of UAV Deployment and Task Computation Offloading Decision in UAV-assisted Edge Computing network 25

Joint Optimization of UAV Deployment and Task Computation Of...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data Science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Liu, Yichuan Tu, Jinbin Wang, Yun School of Computer Science and Engineering Southeast University Key Lab of Computer Network and Information Integration Moe Nanjing China

ISBN: (纸本)9798350330014

The UAVs' deployment decision and task computation offloading decision in the UAV-assisted edge computing network significantly impact the operating efficiency of edge network. On the basis of this, the Optimization Model for UAV Cluster Deployment and Computation Offloading Decision (OMUCDCOD) is established. The model jointly optimizes the number, location of UAV s, and task computation offloading decision. Different from previous studies, this model regards the terminal devices in the edge network as virtual MEC servers, and introduces the collaborative computing mode. The task computation offloading decision made can effectively utilize the computing capabilities offered by the edge network. Considering that the two problems of UAV deployment decision and task computation offloading decision are intricately interconnected, we propose a two-layer optimization algorithm combining K-Means and ant colony algorithm (ToKmAc) to solve OMUCDCOD. ToKmAc is divided into upper and lower layers to solve this optimization problem. The upper layer uses K-Means to solve the UAV deployment decision, that is, the number and location of UAVS;the lower layer employs ant colony algorithm to solve computation offloading decision. Finally, extensive experiments verify the effectiveness of OMUCDCOD and ToKmAc. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

T-Sorokin: A General Mobility Model in Opportunistic networks 26

T-Sorokin: A General Mobility Model in Opportunistic Network...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Tu, Jinbin Li, Qing Wang, Yun Southeast University Key Lab of Computer Network and Information Integration Moe School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350331684

The opportunistic networks are a kind of ad hoc networks that rely on the chance of nodes meeting to transmit messages. Acting as an effective supplement to 4G and 5G networks in some special scenarios where hardware devices are limited, the opportunistic networks have a significant application in health monitoring, warning broadcasting, disaster relief, and so on. The mobility model is one of the research focuses on the opportunistic networks. On the basis of the social mobility theory proposed by Sorokin, a general mobility model, which is suited for various scenarios, called T-Sorokin is proposed. This model is described as a seven-tuple and implemented on the Opportunistic network Environment simulator and fits both Infocom06 and Rome taxi data set, which includes different areas ranging from hotel to city and different mobile units ranging from person to taxi. The results of experiments demonstrate that the T-Sorokin model has the advantage of generality, simplicity, and accuracy. It can simply establish movement tracks close to real data under different scenarios. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A common gateway for interoperability in multi-architecture LVC simulation 6

A common gateway for interoperability in multi-architecture ...

引用

6th International Conference on computer information Science and Application Technology, CISAT 2023

作者： Lin, Shichao Wang, Yun School of Computer Science and Engineering Southeast University Nanjing China Key Lab of Computer Network and Information Integration MOE China

ISBN: (纸本)9781510668546

With the development of Live-Virtual-Constructive (LVC) simulation technology, numerous LVC simulation resources have been developed. To construct more large-scale LVC simulation, it is necessary to integrate existing simulation resources. Due to the heterogeneity of LVC resources, the interoperability between heterogeneous simulation resources becomes a major concern. This paper proposes a common gateway in multi-architecture LVC simulation environment that converts messages between different simulation architectures and achieves a level of semantic interoperability. The gateway provides a collection of protocol-independent interfaces for simulation systems to access co-simulation conveniently. To maintain timing consistency in heterogeneous simulation environments, a time synchronization method is employed to coordinate logical time and real time. Experimental results show that the scheme is flexible and can maintain data transmission latency at a millisecond level in LVC simulation environment, which includes High Level Architecture (HLA), Data Distribution Service (DDS), and Distributed Interactive Simulation (DIS). © 2023 SPIE.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Learning label-specific features for decomposition-based multi-class classification

引用

Frontiers of computer Science 2023年第6期17卷 101-110页

作者： Bin-Bin JIA Jun-Ying LIU Jun-Yi HANG Min-Ling ZHANG College of Electrical and Information Engineering Lanzhou University of TechnologyLanzhou 730050China School of Computer Science and Engineering Southeast UniversityNanjing 210096China Key Laboratory of Computer Network and Information Integration(Ministry of Education) Southeast UniversityNanjing 210096China

Multi-class classification can be solved by decomposing it into a set of binary classification problems according to some encoding rules,e.g.,one-vs-one,one-vs-rest,error-correcting output *** works solve these binary classification problems in the original feature space,while it might be suboptimal as different binary classification problems correspond to different positive and negative *** this paper,we propose to learn label-specific features for each decomposed binary classification problem to consider the specific characteristics containing in its positive and negative ***,to generate the label-specific features,clustering analysis is respectively conducted on the positive and negative examples in each decomposed binary data set to discover their inherent information and then label-specific features for one example are obtained by measuring the similarity between it and all cluster *** clearly validate the effectiveness of learning label-specific features for decomposition-based multi-class classification.

关键词： machine learning multi-class classification error-correcting output codes label-specific features

来源：评论

学校读者我要写书评

暂无评论

A Prediction-Based Fuzzy Method for Multi-objective Microservice Workflows Scheduling 18th

A Prediction-Based Fuzzy Method for Multi-objective Microse...

引用

18th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Xu, Jingwen Chen, Long Li, Xiaoping Wang, Shuang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China

ISBN: (纸本)9789819996391

Microservice workflows are widely used in real-time mobile computing scenarios such as face recognition and speech recognition. The key challenge is to develop efficient, stable, and robust algorithms capable of handling uncertain and fuzzy workflow tasks. In this paper, we consider the real-time microservice workflow fuzzy scheduling problem under VM-Container two-tier resources. A novel model based on triangle fuzzy numbers is formulated. The model encompasses two metrics: cost and degree of satisfaction. In response, this paper proposes an ARIMA prediction-based workflow fuzzy scheduling method (PFSM), comprising five key components: prediction of workflow arrival number, predistribution of task sub-deadlines, ordering of the task pool, task scheduling strategy, and resource management. To assess the performance of the proposed algorithms, several comparison algorithms are selected for analysis, and their performance differences are evaluated using ANOVA. The experimental results demonstrate the significant superiority of the proposed algorithms over the other compared algorithms in terms of overall performance. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Traffic Flow Prediction Based Task Offloading Method in Vehicular Edge Computing 18th

A Traffic Flow Prediction Based Task Offloading Method in V...

引用

18th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Xie, Liqiong Chen, Long Li, Xiaoping Wang, Shuang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China

ISBN: (纸本)9789819996391

Vehicular Edge Computing (VEC) emerges as a promising paradigm by deploying computation and storage resources on edge servers located in close proximity to vehicles, such as roadside units or base stations. This proximity enables VEC to provide abundant resources and low-latency services, catering to the computational needs of vehicles. However, the dynamic nature of traffic flow presents new challenges in terms of task offloading decisions and resource allocation within VEC environments. This paper addresses the task offloading problem in VEC systems, considering the impact of dynamic traffic flow. To address this problem, we formulate an integer programming model that captures the essence of the studied scenario. To devise an efficient solution, we propose a novel traffic flow prediction-based heuristic algorithm (TFPVTO). TFPVTO incorporates different rules and strategies to generate an optimal offloading task sequence, make informed offloading decisions, and allocate resources effectively. To assess the performance of the proposed algorithm, we utilize a real-world traffic flow dataset. In order to fine-tune and optimize the algorithm’s components, we employ a multi-factor analysis of variance (ANOVA) technique. The proposed TFPVTO algorithm is then rigorously compared against other state-of-the-art algorithms, namely TAVF, MONSA, and RANDOM. Through extensive experiments and statistical analysis, we demonstrate the effectiveness and efficiency of the proposed algorithm in terms of task offloading performance. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Deep Spatial Spectral Convolutional Sparse Coding for Spectral CT Image Reconstruction 17

Deep Spatial Spectral Convolutional Sparse Coding for Spectr...

引用

17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Liu, Jin Xie, Jingjing Wang, Kun Qiang, Jun College of Computer and Information Anhui Polytechnic University Wuhu China Southeast University Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing China

ISBN: (纸本)9798331507398

Spectral computed tomography (CT) provides the potential to generate attenuation maps at varying spectral bins, which can subsequently be employed for the resolve of tissue materials. However, the majority of reconstruction algorithms employed for every projection energy bin typically exhibit a considerable degree of noise. Recently, a series of techniques have been designed in spectral CT reconstruction based on traditional iterative models or deep learning (DL) methods. However, these works are independent or simply coupled, often neglecting the dependency relationships of spatial and spectrum. Additionally, the interpretability and generalization capabilities remain as formidable challenges for current methods. To effectively address these challenges, we initially introduce a spatial-spectral convolutional sparse coding (SS-CSC) framework, which aims to jointly represent spatial and spectral features in a unified manner. Subsequently, we devise a novel deep unfolding network, inspired by SS-CSC, for spectral CT image representation. We refer to this component as the SS-CSC module. Furthermore, we expand the iterative reconstruction scheme for constructing an interpretable deep SS-CSC iterative reconstruction network (SS-CSC-Net) model for spectral CT imaging. The SS-CSC-Net is composed of several iteration blocks, with each block containing two modules: image reconstruction and SS-CSC modules. The spectral CT image is updated using a deep learning-based spatial-spectral prior constraint. Experimental results from both qualitative results and quantitative analyses indicate that the proposed SS-CSC-Net excels in noise reduction and in maintaining tissue edge integrity, delivering superior overall performance. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning 30

Few-Shot Semantic Dependency Parsing via Graph Contrastive L...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Li, Bin Fan, Yunlong Sataer, Yikemaiti Shi, Chuanqi Gao, Miao Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education China

ISBN: (纸本)9782493814104

Graph neural networks (GNNs) have achieved promising performance on semantic dependency parsing (SDP), owing to their powerful graph representation learning ability. However, training a high-performing GNN-based model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labeled data. To address this drawback, we propose a syntax-guided graph contrastive learning framework to pre-train GNNs with plenty of unlabeled data and fine-tune pre-trained GNNs with few-shot labeled SDP data. Through extensive experiments conducted on the SemEval-2015 Task 18 English dataset in three formalisms (DM, PAS, and PSD), we demonstrate that our framework achieves promising results when few-shot training samples are available. Furthermore, benefiting from the pre-training process, our framework exhibits notable advantages in the out-of-domain test sets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

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：