检索结果-内蒙古大学图书馆

Neural Network Based on Inter-layer Perturbation Strategy for Text Classification

Machine Intelligence Research 2025年第1期22卷 176-188页

作者： Nai Zhou Nianmin Yao Qibin Li School of Computer Science and Technology Dalian University of TechnologyDalian116024China

Recently,many researches have created adversarial samples to enrich the diversity of training data for improving the text classification performance via reducing the loss incurred in the neural network ***,existing studies have focused solely on adding perturbations to the input,such as text sentences and embedded representations,resulting in adversarial samples that are very similar to the original *** adversarial samples can not significantly improve the diversity of training data,which restricts the potential for improved classification *** alleviate the problem,in this paper,we extend the diversity of generated adversarial samples based on the fact that adding different disturbances between different layers of neural network has different *** propose a novel neural network with perturbation strategy(PTNet),which generates adversarial samples by adding perturbation to the intrinsic representation of each hidden layer of the neural ***,we design two different perturbation ways to perturb each hidden layer:1)directly adding a certain threshold perturbation;2)adding the perturbation in the way of adversarial *** above settings,we can get more perturbed intrinsic representations of hidden layers and use them as new adversarial samples,thus improving the diversity of the augmented training *** validate the effectiveness of our approach on six text classification datasets and demonstrate that it improves the classification ability of the *** particular,the classification accuracy on the sentiment analysis task improved by an average of 1.79%and on question classification task improved by 3.2%compared to the BERT baseline,respectively.

关键词： Perturbation strategy adversarial training machine learning text classification adversarial samples

来源：评论

学校读者我要写书评

暂无评论

Optimizing local search-based partial MaxSAT solving via initial assignment prediction

引用

science China(Information sciences) 2025年第2期68卷 59-73页

作者： Chanjuan LIU Guangyuan LIU Chuan LUO Shaowei CAI Zhendong LEI Wenjie ZHANG Yi CHU Guojing ZHANG School of Computer Science and Technology Dalian University of Technology School of Software Beihang University Institute of Software Chinese Academy of Sciences School of Computer Science Peking University

Partial maximum satisfiability(PMS) is a significant generalization of Boolean satisfiability(SAT) and maximum satisfiability(MaxSAT), by introducing hard clauses and soft clauses. Compared with SAT and MaxSAT, the PMS problem has more real-world applications where both hard and soft constraints are involved. Local search is an effective incomplete method for solving PMS and is useful for important domains where good-quality solutions are desired within reasonable *** local search PMS solvers, the approach for initial assignment generation is crucial because its effectiveness significantly affects practical performance. In this study, we propose a novel initial assignment prediction approach, called InitPMS. When predicting an assignment for PMS, InitPMS considers the specific structure of PMS instances, i.e., distinguishing hard and soft clauses. Our experiments on extensive PMS instances from MaxSAT evaluations(MSEs) 2020 and 2021 show that InitPMS significantly boosts the performance of five state-of-the-art local search PMS solvers, demonstrating its generality. In addition,our results indicate that incorporating InitPMS could improve the performance of one of the best incomplete PMS solvers in MaxSAT Evaluation 2021, indicating that InitPMS might help advance the state of the art in PMS solving.

关键词： MaxSAT local search initial assignment incomplete method assignment prediction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Entity Relationship Extraction in Dialogue Texts Using Hypergraph and Heterogeneous Graph

引用

Chinese Journal of Electronics 2025年第1期34卷 295-308页

作者： Shunmiao Zhang Siyuan Zheng Degen Huang Dan Li School of Computer Science and Mathematics Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology School of Computer Science and Technology Dalian University of Technology Elsevier

Dialogue-based relation extraction(DialogRE) aims to predict relationships between two entities in dialogue. Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dialogue data as well as complex entity relationships, such as a single entity with multiple types of connections. To address these issues, this paper presents a novel approach for dialogue relationship extraction termed the hypergraphs and heterogeneous graphs model(HG2G). This model introduces a two-tiered structure, comprising dialogue hypergraphs and dialogue heterogeneous graphs, to address the shortcomings of existing methods. The dialogue hypergraph establishes connections between similar nodes using hyper-edges and utilizes hypergraph convolution to capture multi-level features. Simultaneously, the dialogue heterogeneous graph connects nodes and edges of different types, employing heterogeneous graph convolution to aggregate cross-sentence information. Ultimately, the integrated nodes from both graphs capture the semantic nuances inherent in dialogue. Experimental results on the DialogRE dataset demonstrate that the HG2G model outperforms existing state-of-the-art methods.

关键词： Convolution Aggregates Semantics Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

DNA sequence design model for multi-scene fusion

引用

Neural Computing and Applications 2025年第7期37卷 5499-5520页

作者： Yao, Yao Zheng, Yanfen Cui, Shuang Hou, Yaqing Zhang, Qiang Wei, Xiaopeng School of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China

Due to its unique properties and excellent sequence design methods, DNA finds wide applications in computing, information storage, molecular circuits, and biological diagnosis. Previous efforts to enhance the efficiency and precision of DNA sequence design have led to the proposal of various universal DNA sequence design methods. These methods optimize the arrangement of the four bases to reduce sequence similarity and meet specific criteria. However, prior investigations have predominantly focused on sequence design within single-scene frameworks, overlooking the complexities associated with designing for multi-scene fusion, such as ion-bridge mismatch, tri-base sequence design, and others. To address this gap, we fused four common scenes and introduced two novel constraint models to facilitate DNA sequence design for multi-scene fusion. Additionally, we developed a dynamic virus spread algorithm as the core for optimizing DNA sequences and evaluated it using 23 well-known benchmark functions. Furthermore, our algorithm outperformed eight popular swarm evolutionary algorithms in eight dominant results. Finally, we simulated the optimization of four distinct scenes, demonstrating that our sequences met expected performance levels in their respective areas. Thus, our work provides a practical tool for designing DNA sequences tailored to various specific applications. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Entity and Relationship Extraction with High-quality Spans and Enhanced Marker Strategies

引用

Machine Intelligence Research 2025年第2期22卷 289-303页

作者： Qibin Li Nianmin Yao Nai Zhou School of Computer Science Dalian University of TechnologyDalian 116024China Ningbo Institute of Dalian University of Technology Ningbo 116026China

Entity and relation extraction is a critical task in information *** approaches have emphasized obtaining improved span ***,existing work suffers from two major ***,there is an overabundance of low-quality candidate spans,which hinders the effective extraction of information from high-quality candidate ***,the information encoded by existing marker strategies is often too simple to fully capture the nuances of the span,resulting in the loss of potentially valuable *** address these issues,we propose an enhancing entity and relation extraction with high-quality spans and enhanced marker(HSEM)strategies,it assigns adaptive weights to different spans in order to make the model more focused on high quality ***,the HSEM model enriches marker representation to incorporate more span information and enhance entity ***,we design a span scoring framework that assesses span quality based on the fusion of internal information and focuses the model on training high-quality samples to improve *** results on six benchmark datasets demonstrate that our model achieves state-of-the-art results after discriminating span quality.

关键词： High-quality spans enhanced marker span scoring framework span representations entity and relation extraction

来源：评论

学校读者我要写书评

暂无评论

Towards Reliable Configuration Management in Clouds: A Lightweight Consistency Validation Mechanism for Virtual Private Clouds

引用

Chinese Journal of Electronics 2025年第1期34卷 49-63页

作者： Yuhang Qiu Gongming Zhao Hongli Xu Long Li He Huang Liusheng Huang School of Computer Science and Technology University of Science and Technology of China Suzhou Institute for Advanced Research University of Science and Technology of China School of Computer Science and Technology Soochow University

The virtual private cloud service currently lacks a real-time end-to-end consistency validation mechanism, which prevents tenants from receiving immediate feedback on their requests. Existing solutions consume excessive communication and computational resources in such large-scale cloud environments, and suffer from poor timeliness. To address these issues, we propose a lightweight consistency validation mechanism that includes real-time incremental validation and periodic full-scale validation. The former leverages message layer aggregation to enable tenants to swiftly determine the success of their requests on hosts with minimal communication overhead. The latter utilizes lightweight validation checksums to compare the expected and actual states of hosts locally, while efficiently managing the checksums of various host entries using inverted indexing. This approach enables us to efficiently validate the complete local configurations within the limited memory of hosts. In summary, our proposed mechanism achieves closed-loop implementation for new requests and ensures their long-term effectiveness.

关键词： Cloud computing Memory management Configuration management Reliability engineering Real-time systems Indexing

来源：评论

学校读者我要写书评

暂无评论

PriChain: Efficient Privacy-Preserving Fine-Grained Redactable Blockchains in Decentralized Settings

引用

Chinese Journal of Electronics 2025年第1期34卷 82-97页

作者： Hongchen Guo Weilin Gan Mingyang Zhao Chuan Zhang Tong Wu Liehuang Zhu Jingfeng Xue School of Computer Science and Technology Beijing Institute of Technology School of Cyberspace Science and Technology Beijing Institute of Technology School of Computer and Communication Engineering University of Science and Technology Beijing

Recently, redactable blockchain has been proposed and leveraged in a wide range of real systems for its unique properties of decentralization, traceability, and transparency while ensuring controllable on-chain data redaction. However, the development of redactable blockchain is now obstructed by three limitations, which are data privacy breaches, high communication overhead, and low searching efficiency, respectively. In this paper, we propose PriChain, the first efficient privacy-preserving fine-grained redactable blockchain in decentralized settings. PriChain provides data owners with rights to control who can read and redact on-chain data while maintaining downward compatibility, ensuring the one who can redact will be able to read. Specifically, inspired by the concept of multi-authority attribute-based encryption, we utilize the isomorphism of the access control tree, realizing fine-grained redaction mechanism, downward compatibility, and collusion resistance. With the newly designed structure, PriChain can realize O（n） communication and storage overhead compared to prior O（n2） schemes. Furthermore, we integrate multiple access trees into a tree-based dictionary, optimizing searching efficiency. Theoretical analysis proves that PriChain is secure against the chosen-plaintext attack and has competitive complexity. The experimental evaluations show that PriChain realizes 10× efficiency improvement of searching and 100× lower communication and storage overhead on average compared with existing schemes.

关键词： Resistance Access control Data privacy Dictionaries Blockchains Encryption Complexity theory Usability Protection

来源：评论

学校读者我要写书评

暂无评论

Model Recovery in Federated Unlearning With Restricted Server Data Resources

引用

IEEE Internet of Things Journal 2025年第11期12卷 17920-17935页

作者： Zhang, Jianxin Zhao, Mengda Wang, Zhenwei Su, Weijian Wang, Pengfei Dalian Minzu University School of Computer Science and Engineering Dalian116600 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Dalian116024 China

Recent model recovery methods in federated unlearning (FUL) either rely on additional communication with the remaining clients or require large amounts of high-quality data from the server for training, overlooking scenarios with limited data resources. Currently, Contrastive Language-Image Pretraining (CLIP) has demonstrated remarkable performance across a wide range of tasks, particularly excelling in few-shot learning scenarios. In this paper, inspired by CLIP, we explore the scenario of few-shot knowledge distillation and propose CLIP-Guided Few-shot Knowledge Distillation (CGKD) for Model Recovery in FUL. CGKD mainly consists of three components: 1) The unlearning module constructs the unlearning model by erasing all historical contributions of the target client, and this model is treated as the student model;2) Fine-tuning the pre-trained CLIP model using few-shot data from the server side to obtain a more robust teacher model (CLIP*);and 3) Model recovery is achieved through knowledge distillation, leveraging the rich visual and semantic knowledge of CLIP∗ to enhance the student model's understanding of image semantic context, thereby improving the performance of the unlearning model. Extensive experimental results demonstrate that CGKD outperforms the compared FUL method in recovery performance across four standard datasets, validating the effectiveness of our approach. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Springback Behavior and Biocompatibility inβ-Type Ti-Mo-O Alloys

引用

Acta Metallurgica Sinica(English Letters) 2025年第2期38卷 313-326页

作者： Cheng Ren Xiaohua Min Sujie Zhang Weiqiang Wang School of Materials Science and Engineering Dalian University of TechnologyDalian 116024China

Ti-Mo-O alloys were used to analyze the effect of Mo and O contents on the mechanical compatibility and *** bending modulus,bending yield strength and springback ratio of the alloys were evaluated by using three-point bending tests and bending load-unloading *** biocompatibility was investigated by the adhesion,proliferation and the alkaline phosphatase(ALP)activity of mouse osteoblast-like cells(MC3T3-E1).The results showed that the bending modulus and bending yield strength first were increased and then decreased with the increase in Mo content,while the springback ratio exhibited an opposite trend to the bending *** the increase in O content,the bending modulus remained almost constant,while the bending yield strength was *** springback ratio exhibited a similar trend to the bending yield *** in vitro biological experiments showed that the Ti-Mo-O alloys had excellent biocompatibility due to the formed stable oxide films on their *** the increase in O and Mo contents,the TiO_(2)-MoO_(2)oxide film became *** with mechanical compatibility and biocompatibility,the Ti-15Mo-0.2O and Ti-15Mo-0.3O alloys were more suitable for the biomedical application of spinal fixation device.

关键词： β-type titanium alloys Bending modulus Bending yield strength Springback Biocompatibility

来源：评论

学校读者我要写书评

暂无评论

Witness encryption with updatable ciphertexts

引用

science China(Information sciences) 2025年第3期68卷 181-196页

作者： Yuzhu WANG Mingwu ZHANG School of Computer Science and Information Security Guilin University of Electronic Technology School of Computer Science Hubei University of Technology

Witness encryption(WE) is a novel type of cryptographic primitive that enables a message to be encrypted via an NP instance. Anyone who possesses a solution to this instance(i.e., a witness) can then recover the message from the *** introduce a variant of WE that allows ciphertext updates, referred to as ciphertext updateable WE(CUWE). With CUWE,a user can encrypt a message using an instance x and a tag t, and those who possess a valid witness w for x and match the access policy defined by tag t can decrypt the message. Furthermore, CUWE allows for the use of an update token to change the tag t of ciphertext to a different tag. This feature enables fine-grained access control, even after the ciphertext has been created, thereby significantly increasing the usefulness of the WE scheme. We demonstrate that such a WE framework with an updatable ciphertext scheme can be constructed using our puncturable instance-based deterministic encryption(PIDE) and indistinguishability obfuscation(iO). We also propose an instantiation of PIDE utilizing puncturable pseudorandom functions(PRFs) that provide(selectively) indistinguishable security. Finally, we expand our CUWE to ciphertext-updatable functional WE(CUFWE), which offers enhanced data access control.

关键词： witness encryption NP relation updatable ciphertext access control indistinguishable obfuscation

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：