检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yang, Dongjie Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions have limited answers and need to respond more deterministically but some do not. We refer to this as question awareness of LLMs. The lack of question awareness in LLMs leads to two phenomena that LLMs are: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions. In this paper, we first evaluate the question awareness in LLMs. The experimental results show that LLMs have the issues of lacking awareness of questions in certain domains, e.g. factual knowledge, resulting in hallucinations during the generation. To mitigate these, we propose a method called Question Awareness Temperature Sampling (QuATS). This method enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. The automatic adjustment in QuATS eliminates the need for manual temperature tuning in text generation and consistently improves model performance in various benchmarks. © 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

KAN v.s. MLP for Offline Reinforcement Learning

KAN v.s. MLP for Offline Reinforcement Learning

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guo, Haihong Li, Fengxin Li, Jiao Liu, Hongyan School of Information Renmin University of China China Institute of Medical Information Medical Library Chinese Academy of Medical Sciences Peking Union Medical College China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Economics and Management Tsinghua University China

ISBN: (纸本)9798350368741

Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used Multi-Layer Perceptions (MLP). Experiments in various fields demonstrated that KAN-based machine learning can achieve comparable if not better performance than MLP-based methods, but with much smaller parameter scales and are more explainable. In this paper, we explore the incorporation of KAN into the actor and critic networks for offline reinforcement learning (RL). We evaluated the performance, parameter scales, and training efficiency of various KAN and MLP-based conservative Q-learning (CQL) on the classical D4RL benchmark for offline RL. Our study demonstrates that KAN can achieve performance close to the commonly used MLP with significantly fewer parameters. This allows us to choose the base networks according to the offline RL task requirements. © 2025 IEEE.

关键词： KAN Kolmogorov-Arnold networks MLP multilayer perceptrons offline reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Federated Domain Generalization for Fault Diagnosis: Cross-Client Style Integration and Dual Alignment Representation

引用

IEEE Internet of Things Journal 2025年第13期12卷 23297-23308页

作者： Wang, Yu Zhang, Guowei Kong, Xianguang Du, Jingli Ma, Hongbo Yunnan Agricultural University College of Big Data Kunming650500 China Xidian University College of Mechanical and Electrical Engineering Xian710071 China State Key Laboratory of Electromechanical Integrated Manufacturing of High-performance Electronic Equipments China

Federated learning (FL) enables the collaborative training of intelligent diagnostic models across multiple clients while preserving data privacy. However, the complex and dynamic working conditions often cause federated diagnostic models to suffer from performance degradation when applied to unseen clients, exposing deficiencies in model generalization. Domain generalization fault diagnosis methods aim to enhance model adaptability under unknown working conditions, but most existing algorithms rely on shared data, making them unsuitable for direct application in federated learning environments. To address this challenge, we propose a federated domain generalization fault diagnosis method based on Cross-Client Style Integration and Dual Alignment representation (CCSIDA). This method significantly enhances model generalization in FL settings while ensuring data privacy. Specifically, CCSIDA integrates three key strategies: cross-client style data enhancement, domain-sensitive feature suppression, and predictive alignment. For cross-client style integration, we design a stochastic mixed-style sample generation module to overcome the limitations of conventional domain generalization data enhancement methods in FL. This module generates diverse samples by constructing a shared style repository, enabling inter-client style information transfer. For cross-client dual alignment representation, we introduce a domain-sensitive feature suppression strategy to reduce domain discrepancies between original and enhanced samples. Additionally, Jensen-Shannon divergence is employed to ensure prediction consistency between these samples. Finally, extensive experiments on five benchmark datasets validate the effectiveness of the proposed method. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust primary quantization step estimation on resized and double JPEG compressed images

引用

Multimedia Tools and Applications 2025年第12期84卷 11097-11118页

作者： Zhang, Lei Chen, XuGuang Niu, YaKun Zuo, XianYu Wang, Huaqing School of Computer and Information Engineering Henan Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng Henan Henan Kaifeng475004 China National Internet Emergency Center Henan Zhengzhou450000 China

As one of the most important forensic tasks, reconstruction of the original information in tampered images is a key step for tampering detection and localization. Currently, a number of methods have been designed to estimate the primary quantization steps of double compressed JPEG images. However, the estimation in the presence of resizing operation remains a challenge. In this paper, we propose a robust primary quantization steps estimation method on resized and double JPEG compressed images. Specifically, the distribution of Discrete Cosine Transform (DCT) coefficients is firstly analyzed on the inverse resized image. Then, a maximum likelihood function together with a filtering strategy is designed to obtain the primary quantization step on Alternating Current (AC) bands. In addition, we find the prominent peak in the Discrete Fourier Transform (DFT) spectrum of the distribution of Direct Current (DC) coefficients is nonlinearly related to the step. Based on this observation, a mapping function derived from the geometric fitting is proposed to estimate the step on DC band. Experimental results demonstrate the proposed method provides superior estimation performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

APIBeh: Learning Behavior Inclination of APIs for Malware Classification 35

APIBeh: Learning Behavior Inclination of APIs for Malware Cl...

引用

35th IEEE International Symposium on Software Reliability engineering, ISSRE 2024

作者： Cui, Lei Zhu, Yiran Yin, Junnan Hao, Zhiyu Wang, Wei Liu, Peng Yang, Ziqi Yun, Xiaochun Zhongguancun Laboratory China Zhejiang University The State Key Laboratory of Blockchain and Data Security China China Guangxi Normal University School of Computer Science and Engineering China

ISBN: (纸本)9798350353884

Malware classification involves categorizing mal-ware samples based on their characteristics. While deep learning techniques applied to malware execution traces, mainly API calls, have shown potential in this field, they still perform poorly. This is primarily because they treat all APIs equally and train classifiers directly on native APIs, which inadequately capture the under-lying family-related semantics. In this paper, we first investigate the behaviors of multiple malware families and observe that different families exhibit divergent behaviors, with each family consistently favoring certain behaviors over time. Motivated by this, we propose APIBeh, a new embedding method designed to enhance malware classification. APIBeh first utilizes Benignity Degree Algorithm to identify and exclude insignificant, likely benign APIs from sequences. Then, it introduces the concept of Behavior Inclination, which quantifies the association between an API and malicious behaviors, facilitating high-level behavior encoding for each API. This Behavior Inclination embedding is then concatenated with raw embedding to represent an API, and fed into a DL model for classifier training. Experimental results show that APIBeh outperforms existing embedding methods in classification performance, e.g., 3.18% boost in weighted f1-score over a recent study using word2vec. In addition, it offers robustness to concept drift and adversarial attacks. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

On the parameterized complexity of minimum/maximum degree vertex deletion on several special graphs

引用

Frontiers of Computer Science 2023年第4期17卷 97-107页

作者： Jia LI Wenjun LI Yongjie YANG Xueying YANG School of Information Engineering Hunan Industry PolytechnicChangsha 410036China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication EngineeringChangsha University of Science and TechnologyChangsha 410015China Chair of Economic Theory Saarland UniversitySaarbrücken 66123Germany

In the minimum degree vertex deletion problem,we are given a graph,a distinguished vertex in the graph,and an integer κ,and the question is whether we can delete at most κ vertices from the graph so that the distinguished vertex has the unique minimum *** maximum degree vertex deletion problem is defined analogously but here we want the distinguished vertex to have the unique maximum *** is known that both problems areΨ-hard and fixed-parameter intractable with respect to some natural *** this paper,we study the(parameterized)complexity of these two problems restricted to split graphs,p-degenerate graphs,and planar *** study provides a comprehensive complexity landscape of the two problems restricted to these special graphs.

关键词： minimum degree maximum degree vertex deletion split graphs planar graphs parameterized complexity

来源：评论

学校读者我要写书评

暂无评论

Cross-Chain Privacy-Preserving for BIoMT With Designated Verifier Proxy Signature

引用

IEEE Internet of Things Journal 2025年第12期12卷 20042-20055页

作者： Li, Chaoyang Jiang, Bohao Dong, Mianxiong Chen, Yuling Huang, Min Xin, Xiangjun Ota, Kaoru Zhengzhou University of Light Industry College of Software Engineering Zhengzhou450001 China Muroran Institution of Technology Muroran050-8585 Japan Guizhou University State Key Laboratory of Public Big Data Guizhou Guiyang550025 China

Blockchain-enabled Internet of Medical Things (BIoMT) has received extensive attention and in-depth research to solve the centralized, data island problems with the rapid developments of blockchain-related technologies. However, many different chains with different data structures, consensus protocols, and cryptographic algorithms are constructed, which brings a new »data island» problem. Meanwhile, the cryptographic algorithms used in most current BIoMT systems are weak against quantum attacks. In this paper, a cross-chain privacy-preserving (CCPP) model and a designated verifier proxy signature (DVPS) scheme have been proposed. This CCPP model is equipped with the relay chain technology and DVPS to achieve secure cross-chain medical data-sharing among different BIoMT systems. The DVPS scheme is constructed with lattice theory, which can achieve signer proxy, designated user verification, and anti-quantum attack. Then, the security proof shows that the proposed DVPS can capture the security properties of correctness, unforgeability, the signer's anonymity, and non-transferability. The performance evaluations show that the cross-chain transactions are efficient and stable with the transaction number increasing, and the proposed DVPS is efficient about the key size, time consumption, and energy consumption. This work can also improve the privacy security of system users and medical data in BIoMT systems and promote the value play of medical data. © 2014 IEEE.

关键词： Lattice theory

来源：评论

学校读者我要写书评

暂无评论

Semi-Asynchronous Federated Split Learning for Computing-Limited Devices in Wireless Networks

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 5196-5212页

作者： Ao, Huiqing Tian, Hui Ni, Wanli Nie, Gaofeng Niyato, Dusit Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Tsinghua University Department of Electronic Engineering Beijing100084 China Nanyang Technological University College of Computing and Data Science Singapore

The rapid evolution of edge computing and artificial intelligence (AI) paves the way for pervasive intelligence in the next-generation network. As a hybrid training paradigm, federated split learning (FSL) leverages data and model parallelism to enhance training efficiency. However, existing FSL encounters unacceptable waiting latency due to device heterogeneity and synchronous model aggregation. To address this issue, we propose a semi-asynchronous FSL (SAFSL) framework that enables personalized model splitting and aperiodic model aggregation. We derive the convergence upper bound by considering factors such as the number of devices, training iterations, and data heterogeneity. To minimize the long-term average training latency while maintaining high energy efficiency in resource-constrained wireless networks, we formulate a stochastic mixed-integer nonlinear programming problem. By decomposing it into multiple sub-problems in each round, we propose a Lyapunov-based alternating optimization algorithm to solve it in an online manner. Numerical results demonstrate that our SAFSL achieves faster convergence with reduced communication overhead while maintaining high prediction performance under non-independent and identically distributed data, outperforming state-of-the-art benchmarks. Moreover, our algorithm achieves a low training latency, highlighting its superior performance and effectiveness. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Semantic Type Identification for Relational Attributes

引用

Journal of Computer Science & Technology 2023年第4期38卷 927-946页

作者：丁玥郭雨荷卢卫李海翔张美慧李晖潘安群杜小勇 Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China Tencent(Beijing)Technology Company Limited Beijing 100080China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China College of Computer Science and Technology Guizhou UniversityGuiyang 550025China Tencent(Shenzhen)Technology Company Limited Shenzhen 518057China

Identifying semantic types for attributes in relations,known as attribute semantic type(AST)identification,plays an important role in many data analysis tasks,such as data cleaning,schema matching,and keyword search in ***,due to a lack of unified naming standards across prevalent information systems(*** islands),AST identification still remains as an open *** tackle this problem,we propose a context-aware method to figure out the ASTs for relations in this *** transform the AST identification into a multi-class classification problem and propose a schema context aware(SCA)model to learn the representation from a collection of relations associated with attribute values and schema *** on the learned representation,we predict the AST for a given attribute from an underlying relation,wherein the predicted AST is mapped to one of the labeled *** improve the performance for AST identification,especially for the case that the predicted semantic types of attributes are not included in the labeled ASTs,we then introduce knowledge base embeddings(***)to enhance the above representation and construct a schema context aware model with knowledge base enhanced(SCA-KB)to get a stable and robust *** experiments based on real datasets demonstrate that our context-aware method outperforms the state-of-the-art approaches by a large margin,up to 6.14%and 25.17%in terms of macro average F1 score,and up to 0.28%and 9.56%in terms of weighted F1 score over high-quality and low-quality datasets respectively.

关键词： attribute semantic type(AST)identification context-aware semantic embedding knowledge base embedding

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：