检索结果-内蒙古大学图书馆

Discourse Component Recognition via Graph Neural Network in Chinese Student Argumentative Essays 1

15th International Conference on Knowledge Science, Engineering, and Management (KSEM)

作者： Wang, Sijie Zhang, Ziwen Dou, Yong Luo, Jun Huang, Zhen Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (数字)9783031109836

ISBN: (纸本)9783031109836;9783031109829

Identifying and classifying original discourse components is a prerequisite task for constructing the knowledge graph structure. Previous work suffers from the following problems. (i) Existing methods only rely on the discourse components themselves to extract the features of the text, and do not fully take into account the potential help of the context information of the discourse to consummate its own features. (ii) Most of the current methods usually combine multiple tasks for joint inference, with complementary effects among them, lacking methods focusing on the single-target task of discourse component recognition. To address these issues, we propose a graph neural network-based discourse component recognition model (DCRGNN), which enhances the interaction of sentence-level discourse component features through graph structure. Our experimental results show that DCRGNN achieves a relative improvement of up to 6% on Macro-F1 for specific discourse component types compared to the previous state-of-the-art methods on the Chinese dataset, and exceeds the baseline model in the single-target task on the English dataset.

关键词： Discourse component recognition Single-target task Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Foolmix: Strengthen the Transferability of Adversarial Examples by Dual-Blending and Direction Update Strategy

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 5286-5300页

作者： Li, Zhankai Wang, Weiping Li, Jie Chen, Kai Zhang, Shigeng Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Sci & Technol Parallel & Distributed Proc Lab PDL Changsha 410073 Peoples R China

Adversarial example attacks are deemed to be a serious threat to deep neural network (DNN) models. Generating adversarial examples in white-box settings has been well-studied, however, it remains challenging to generate transferable adversarial examples that successfully attack black-box models. This work proposes Foolmix, a novel method for generating transferable adversarial examples for black-box attacks. The design of Foolmix is inspired by our observation that adversarial examples with high transferability usually carry multi-class features in the latent space of DNN models. Thus, we propose a dual-blending strategy that blends the image with a set of random pixel-blocks and blends the gradient by calculating the loss of the blended image for both the ground-truth label and a set of random labels. The dual-blending strategy pressures the example to penetrate multiple class regions and gain multi-class features in the latent space, greatly enhancing the transferability of the generated adversarial example. However, the randomness in the blending process might also pressure the example to approach the boundary of the original class region, which lowers the robustness of the example. To mitigate this problem, we further propose an update method in the starting forward direction to guide the generated adversarial example to go deep into multi-class adversarial regions while being globally far away from the original class region. Compared to state-of-the-art transformation-based attacks, Foolmix significantly enhances the transferability of generated adversarial examples, boosting the average transferable attack success rate by 13.2% and 16.9% on mainstream CNNs and ViTs respectively, while achieving better defense breakthrough ability.

关键词： Adversarial machine learning blending strategy cross-architecture attack transferable adversarial examples

来源：评论

学校读者我要写书评

暂无评论

UCG: A Universal Cross-Domain Generator for Transferable Adversarial Examples

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 3023-3037页

作者： Li, Zhankai Wang, Weiping Li, Jie Chen, Kai Zhang, Shigeng Cent South Univ Sch Comp Sci & Engn Changsha 410073 Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Sci & Technol Parallel & Distributed Proc Lab PDL Changsha 410073 Peoples R China

Generating transferable adversarial examples is a challenging issue in adversarial attacks. Existing works on transferable adversarial examples generation mainly focus on models with similar architectures and trained on the same data domain. However, in practice, information such as the model architecture type and training data domain is unlikely to be revealed in deployed models. In this work, we introduce the Universal Cross-domain Generator (UCG), a pioneering framework for transferable adversarial examples that is the first to simultaneously address both cross-domain and cross-architecture challenges in adversarial attacks. The design of UCG is mainly inspired by two key observations. First, there exists some commonality in attention regions even when the structures of models are different. Second, there exists prevalent instability of intermediate-feature maps across cross-domain models. We accordingly design an attention transfer mechanism and a roughness abatement mechanism to enhance the cross-architecture and cross-domain transferability of the generated adversarial examples. Moreover, we propose an integrated transformation processing technique to improve the transferability of the generated adversarial examples under different transformations. Experimental results demonstrate that, compared with state-of-the-art solutions, UCG improves the average transferable attack success rate by 14.6%, 7.8%, and 7.9% in the cross-architecture task (convolutional neural networks (CNNs) to vision transformers (ViTs)), coarse-grained cross-domain tasks, and fine-grained cross-domain tasks, respectively.

关键词： Generators Data models Iterative methods Task analysis Adaptation models Training data Perturbation methods Adversarial machine learning cross-architecture cross-domain generator transferable adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Multi-task Pre-training Language Model for Semantic Network Completion

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION procESSING 2023年第11期22卷 1-20页

作者： Li, Da Zhu, Boqing Yang, Sen Xu, Kele Yi, Ming He, Yukai Wang, Huaimin Tencent Beijing 100084 Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Acad Mil Med Sci Bioinformat Ctr Beijing 100071 Peoples R China

Semantic networks, exemplified by the knowledge graph, serve as a means to represent knowledge by leveraging the structure of a graph. While the knowledge graph exhibits promising potential in the field of natural language processing, it suffers fromincompleteness. This article focuses on the task of completing knowledge graphs by predicting linkages between entities, which is fundamental yet critical. Traditional methods based on translational distance struggle when dealing with unseen entities. In contrast, semantic matching presents itself as a potential solution due to its ability to handle such cases. However, semantic matching-based approaches necessitate large-scale datasets for effective training, which are typically unavailable in practical scenarios, hindering their competitive performance. To address this challenge, we propose a novel architecture for knowledge graphs known as LP-BERT, which incorporates a language model. LP-BERT consists of two primary stages: multi-task pre-training and knowledge graph fine-tuning. During the pre-training phase, the model acquires relationship information from triples by predicting either entities or relations through three distinct tasks. In the fine-tuning phase, we introduce a batch-based triple-style negative sampling technique inspired by contrastive learning. This method significantly increases the proportion of negative sampling while maintaining a nearly unchanged training time. Furthermore, we propose a novel data augmentation approach that leverages the inverse relationship of triples to enhance both the performance and robustness of the model. To demonstrate the effectiveness of our proposed framework, we conduct extensive experiments on three widely used knowledge graph datasets: WN18RR, FB15k-237, and UMLS. The experimental results showcase the superiority of our methods, with LP-BERT achieving state-of-the-art performance on the WN18RR and FB15k-237 datasets.

关键词： Knowledge graph link prediction semantic matching translational distance multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing VLIW Instruction Scheduling via a Two-Dimensional Constrained Dynamic Programming

引用

ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS 2024年第5期29卷 1-20页

作者： Deng, Can Chen, Zhaoyun Shi, Yang Ma, Yimin Wen, Mei Luo, Lei Natl Univ Def Technol Coll Comp Deya Rd Changsha 410000 Hunan Peoples R China Key Lab Adv Microprocessor Chips & Syst Changsha 410000 Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Deya Rd Changsha 410073 Hunan Peoples R China

Typical embedded processors, such as Digital Signal processors (DSPs), usually adopt Very Long Instruction Word (VLIW) architecture to improve computing efficiency. The performance of VLIW processors heavily relies on Instruction-Level parallelism (ILP). Therefore, it is crucial to develop an efficient instruction scheduling algorithm to explore more ILP. While heuristic algorithms are widely used in modern compilers due to simple implementation and low computational cost, they have limitations in providing accurate solutions and are prone to local optima. On the other hand, exact algorithms can usually find the optimal solution, but their high time overhead makes them less suitable for large-scale problems. This article proposes a twodimensional constrained dynamic programming (TDCDP) approach and a quantitative model for instruction scheduling. The TDCDP approach achieves near-optimal solutions within an acceptable time overhead. Furthermore, we integrate our TDCDP approach into mainstream compiler architecture, encompassing Pre- and Post-RA (register allocation) scheduling. We conduct a quantitative evaluation of TDCDP compared with four heuristic algorithms on a typical VLIW processor. Our approach achieves an efficiency improvement of up to 58.34% in final solutions compared with the heuristic algorithms. Additionally, the Post-RA Scheduling enhances programs with an average speedup of 14.04% than solely applying the Pre-RA Scheduling.

关键词： Embedded system instruction scheduling quantitative analysis dynamic programming VLIW

来源：评论

学校读者我要写书评

暂无评论

SCGraph: Accelerating Sample-based GNN Training by Staged Caching of Features on GPUs 20

SCGraph: Accelerating Sample-based GNN Training by Staged Ca...

引用

20th IEEE Int Symposium on parallel and distributed processing with Applicat / 15th IEEE Int Conf on Social Comp and Networking / 12th IEEE Int Conf on Big Data and Cloud Comp / 12th IEEE Int Conf on Sustainable Comp and Commun

作者： He, Yuqi Lai, Zhiquan Ran, Zhejiang Zhang, Lizhi Li, Dongsheng Natl Univ Def Technol Coll Comp Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9781665464970

Graph neural networks (GNNs) have been becoming important tools for processing structured graph data and successfully applied to multiple graph-based application scenarios. The existing GNN systems adopt sample-based training on large-scale graphs over multiple GPUs. Although they support large-scale graph training, large data loading overhead of transferring vertex features between CPUs and GPUs is still a bottleneck. In this work, we propose SCGraph, a method that supports GPU high-speed feature caching. SCGraph classifies the graph vertices sorted by out-degrees. For high out-degree vertices, SCGraph sets grading caches via different GPUs to increase the overall cache content through NVLink high-speed data transmission between them. For low out-degree vertices, SCGraph expands training vertices' neighborhood in advance to regenerate cache. We evaluate SCGraph against two state-of-the-art industrial GNN frameworks, i.e., DGL and PaGraph on various benchmarks. Experimental results show that SCGraph improves the cache hit rate over GPUs up to 23.6%, and achieves up to 1.71x performance speedup over the state-of-the-art baselines while the convergence almost constant.

关键词： graph neural networks feature caching sampling

来源：评论

学校读者我要写书评

暂无评论

Multi-level Contrastive Learning for Commonsense Question Answering 16th

Multi-level Contrastive Learning for Commonsense Question An...

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Fang, Quntian Huang, Zhen Zhang, Ziwen Hu, Minghao Hu, Biao Wang, Ankun Li, Dongsheng Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China Informat Res Ctr Mil Sci Beijing Peoples R China

ISBN: (纸本)9783031402913;9783031402920

Recent studies have shown that the integration of external knowledge greatly improves the performance of commonsense question answering. However, the problems of semantic representation discrepancy between questions and external knowledge as well as weak discrimination between choices have not been well ameliorated. To address the above problems, we propose Multi-Level Contrastive Learning named MLCL for commonsense question answering, which includes instance-level and class-level contrastive learning modules. The instance-level contrastive module aims to align questions with knowledge of correct choice in semantic space, and class-level contrastive module focuses on how to make it easier to distinguish between correct and wrong choices. The model achieves state-of-the-art result in CommonsenseQA dataset and outperforms competitive approaches in OpenBookQA. In addition, adequate experiments verify the effectiveness of contrastive learning in multi-choice commonsense question answering.

关键词： Contrastive learning Commonsense question answering External knowledge

来源：评论

学校读者我要写书评

暂无评论

HyperPart: A Hypergraph-Based Abstraction for Deduplicated Storage Systems

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2025年第1期13卷 46-60页

作者： Cheng, Geyao Xia, Junxu Luo, Lailong Mi, Haibo Guo, Deke Ma, Richard T. B. Natl Univ Def Technol Coll Informat & Commun State Key Lab Complex & Crit Software Environm Wuhan 430019 Peoples R China Natl Univ Def Technol Natl Key Lab Informat Syst Engn Changsha 410073 Peoples R China Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Singapore Sch Comp Singapore 119077 Singapore

Currently, deduplication techniques are utilized to minimize the space overhead by deleting redundant data blocks across large-scale servers in data centers. However, such a process exacerbates the fragmentation of data blocks, causing more cross-server file retrievals with plummeting retrieval throughput. Some attempts prefer better file retrieval performance by confining all blocks of a file to one single server, resulting in non-trivial space consumption for more replicated blocks across servers. An ideal network storage system, in effect, should take both the deduplication and retrieval performance into account by implementing reasonable assignment of the detected unique blocks. Such a fine-grained assignment requires an accurate and comprehensive abstraction of the files, blocks, and the file-block affiliation relationships. To achieve this, we innovatively design the weighted hypergraph to profile the multivariate data correlations. With this delicate abstraction in place, we propose HyperPart, which elegantly transforms this complex block allocation problem into a hypergraph partition problem. For more general scenarios with dynamic file updates, we further propose a two-phase incremental hypergraph repartition scheme, which mitigates the performance degradation with minimal migration volume. We implement a prototype system of HyperPart, and the experiment results validate that it saves around 50% of the storage space and improves the retrieval throughput by approximately 30% of state-of-the-art methods under the balance constraints.

关键词： Servers Fingerprint recognition Throughput Metadata Resource management Switches Data centers Indexing Ethernet Correlation Network storage systems data deduplication hypergraph partition

来源：评论

学校读者我要写书评

暂无评论

HSS: A Hierarchical Semantic Similarity Hard Negative Sampling Method for Dense Retrievers 29th

HSS: A Hierarchical Semantic Similarity Hard Negative Sampli...

引用

29th International Conference on MultiMedia Modeling (MMM)

作者： Xie, Xinjia y Liu, Feng Gai, Shun Huang, Zhen Hu, Minghao Wang, Ankun Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410000 Peoples R China Informat Res Ctr Mil Sci Beijing 100000 Peoples R China

ISBN: (纸本)9783031278174;9783031278181

Dense Retriever (DR) for Open-domain textual question answering (OpenQA), which aims to retrieve passages from large data sources like Wikipedia or Google, has gained wide attention in recent years. Although DR models continuously refresh state-of-the-art performances, their improvement relies on negative sampling during the training process. Existing sampling strategies mainly focus on developing a complex algorithm based on computer science, and ignore the abundant semantic features of datasets. We discover that there exists obvious changes in semantic similarity and present a three-level hierarchy of semantic similarity: same topic, same class, other class, whose rationality is further demonstrated by ablation study. Based on this, we propose a hard negative sampling strategy named Hierarchical Semantic Similarity (HSS). Our HSS model performs negative sampling at semantic levels of topic and class, and experimental results on four datasets show that it achieves comparable or better retrieval performance compared with existing competitive baselines. The code is available in https://***/redirecttttt/HSS.

关键词： Negative sampling Dense Retriever Semantic Similarity Open-domain question answering

来源：评论

学校读者我要写书评

暂无评论

Bi-Objective Scheduling Algorithm for Hybrid Workflow in JointCloud 15

Bi-Objective Scheduling Algorithm for Hybrid Workflow in Joi...

引用

15th IEEE International Conference on Joint Cloud Computing (JCC)

作者： Li, Rui Wang, Huaimin Shi, Peichang Natl Univ Def Technol Coll Comp Sci Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Sci State Key Lab Complex & Crit Software Environm Changsha 410073 Peoples R China

ISBN: (纸本)9798350387339

Big data workflows are widely used in IoT, recommended systems, and real-time vision applications, and they continue to grow in complexity. These hybrid workflows consist of both resource-intensive batch jobs and latency-sensitive stream jobs. Examples include the data analytics workflow, which incorporates batch data transformations and low-latency querying, and the machine learning workflow, which processes stream data feature extraction before performing batch training and low-latency inference. However, existing research on workflow scheduling primarily focuses on either stream or batch workflows, neglecting the efficient scheduling of hybrid workflows that respect their diverse resource requirements and the costly data transfers between them. In this article, we propose a hybrid workflow model that defines the optimal placement of hybrid workflows (OHWP) as a bi-objective optimization problem. Our proposed model takes into account parameters related to inter-communication between stream and batch jobs, as well as the heterogeneous resources in JointCloud environment. Additionally, we present OHWP-PS (OHWP on a Pruned Space), a scheduling algorithm for hybrid workflows that minimizes both cost and latency by improving the initial population and dynamically updating the search space. The results demonstrate that the proposed OHWP-PS algorithm is effective and competitive across all experiments.

关键词： batch and stream workflow scheduling hybrid workflow JointCloud bi-object optimization

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：