检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Qingxiao Sun Yi Liu Hailong Yang Zhonghui Jiang Zhongzhi Luan Depei Qian State Key Laboratory of Software Development Environment Beijing China School of Computer Science and Engineering Beihang University Beijing China

Stencil computations are widely used in high performance computing (HPC) applications. Many HPC platforms utilize the high computation capability of GPUs to accelerate stencil computations. In recent years, stencils have become more diverse in terms of stencil order, memory accesses and computation patterns. To adapt diverse stencils to GPUs, a variety of optimization techniques have been proposed such as streaming and retiming. However, due to the diversity of stencil patterns and GPU architectures, no single optimization technique fits all stencils. Besides, it is challenging to choose the most cost-efficient GPU for accelerating target stencils. To address the above problems, we propose StencilMART, an automatic optimization selection framework that predicts the best optimization combination and execution time under a certain parameter setting for stencils on GPUs. Specifically, the StencilMART represents the stencil patterns as binary tensors and neighboring features through tensor assignment and feature extraction. In addition, the StencilMART implements various machine learning methods such as classification and regression that utilize stencil representation and hardware characteristics for execution time prediction. The experiment results show that the StencilMART can achieve accurate optimization selection and performance prediction for various stencils across GPUs.

关键词： Distributed processing Tensors High performance computing Graphics processing units Machine learning computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

TUBENCH: BENCHMARKING LARGE VISION-LANGUAGE MODELS ON TRUSTWORTHINESS WITH UNANSWERABLE QUESTIONS

arXiv

引用

arXiv 2024年

作者： He, Xingwei Zhang, Qianru Jin, A-Long Yuan, Yuan Yiu, Siu-Ming The University of Hong Kong Hong Kong Xi’an Jiaotong-Liverpool University China School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment China Zhongguancun Laboratory China

Large Vision-Language Models (LVLMs) have achieved remarkable progress on visual perception and linguistic interpretation. Despite their impressive capabilities across various tasks, LVLMs still suffer from the issue of hallucination, which involves generating content that is incorrect or unfaithful to the visual or textual inputs. Traditional benchmarks, such as MME and POPE, evaluate hallucination in LVLMs within the scope of Visual Question Answering (VQA) using answerable questions. However, some questions are unanswerable due to insufficient information in the images, and the performance of LVLMs on such unanswerable questions remains underexplored. To bridge this research gap, we propose TUBench, a benchmark specifically designed to evaluate the reliability of LVLMs using unanswerable questions. TUBench comprises an extensive collection of high-quality, unanswerable questions that are meticulously crafted using ten distinct strategies. To thoroughly evaluate LVLMs, the unanswerable questions in TUBench are based on images from four diverse domains as visual contexts: screenshots of code snippets, natural images, geometry diagrams, and screenshots of statistical tables. These unanswerable questions are tailored to test LVLMs’ trustworthiness in code reasoning, commonsense reasoning, geometric reasoning, and mathematical reasoning related to tables, respectively. We conducted a comprehensive quantitative evaluation of 28 leading foundational models on TUBench, with Gemini-1.5-Pro, the top-performing model, achieving an average accuracy of 69.2%, and GPT-4o, the third-ranked model, reaching 66.7% average accuracy, in determining whether questions are answerable. Furthermore, our manual analysis of the model outputs reveals that: (1) Gemini-1.5-Pro provides both correct answers and explanations in only 41% of cases, and (2) hallucinations are the primary cause of error, accounting for 58.5% of the incorrect explanations generated by Gemini-1.5-Pro. These findings

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Imperceptible Face Forgery Attack via Adversarial Semantic Mask

arXiv

引用

arXiv 2024年

作者： Liu, Decheng Su, Qixuan Peng, Chunlei Wang, Nannan Gao, Xinbo State Key Laboratory of Integrated Services Networks School of Cyber Engineering Xidian University Shaanxi Xi’an710071 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Xidian University Shaanxi Xi’an710071 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

With the great development of generative model techniques, face forgery detection draws more and more attention in the related field. Researchers find that existing face forgery models are still vulnerable to adversarial examples with generated pixel perturbations in the global image. These generated adversarial samples still can't achieve satisfactory performance because of the high detectability. To address these problems, we propose an Adversarial Semantic Mask Attack framework (ASMA) which can generate adversarial examples with good transferability and invisibility. Specifically, we propose a novel adversarial semantic mask generative model, which can constrain generated perturbations in local semantic regions for good stealthiness. The designed adaptive semantic mask selection strategy can effectively leverage the class activation values of different semantic regions, and further ensure better attack transferability and stealthiness. Extensive experiments on the public face forgery dataset prove the proposed method achieves superior performance compared with several representative adversarial attack methods. The code is publicly available at https://***/clawerO-O/ASMA. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Solving Math Word Problems Following Logically Consistent Template

Solving Math Word Problems Following Logically Consistent Te...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zeyu Huang Xiaofeng Zhang Jun Bai Wenge Rong Yuanxin Ouyang Zhang Xiong State Key Laboratory of Software Development Environment Beihang University Beijing China Sino-French Engineer School Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between Questions and plays a crucial role in our model's nerformance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disentangled Hypergraph Collaborative Filtering for Social Recommendation

Disentangled Hypergraph Collaborative Filtering for Social R...

引用

IEEE International Conference on Web Services (ICWS)

作者： Xiao Liu Shunmei Meng Qianmu Li Xiaolong Xu Lianyong Qi Wanchun Dou Jing Zhang Xuyun Zhang Nanjing University of Science and Technology China State Key Lab. for Novel Software Technology Nanjing University China School of Computer and Software Nanjing University of Information Science and Technology China College of Computer Science and Technology China University of Petroleum (East China) China School of Cyber Science and Engineering Southeast University China School of Computing Macquarie University Australia

In the current era of information overload, service recommendations have emerged as a valuable tool for enhancing the user experience. Among them, social recommendation models have shown promising results by incorporating social relationships to improve representation learning. However, most of these models lack fine-grained modeling of social user behavior, leading to a unified representation of users and a loss of expressiveness in user representations. To address this issue, we propose DisenHGCF, a new social recommendation approach based on disentangled hypergraph collaborative filtering, to disentangle the representations of users and items at the granularity of social users’ intents. This approach aims to provide a more nuanced understanding of the user, leading to more accurate and personalized recommendations. To be specific, DisenHGCF leverages hypergraphs to represent the complex relationships among users, friends, and items. By using the hypergraph disentangling module based on attention, it is able to disentangle the user’s intents and generate users representations in cooperating their intents for recommendation tasks. Additionally, a contrastive learning task based on intent-weight perturbation is designed to enhance representational learning. The experimental results obtained from the BeiBei and Beidian datasets demonstrate the superiority of our proposed approach in comparison to previous baseline methods, as evidenced by higher Recall and NDCG scores.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuro-symbolic learning yielding logical constraints 23

Neuro-symbolic learning yielding logical constraints

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zenan Li Yunpeng Huang Zhaoyu Li Yuan Yao Jingwei Xu Taolue Chen Xiaoxing Ma Jian Lü State Key Lab of Novel Software Technology Nanjing University China Department of Computer Science University of Toronto Canada School of Computing and Mathematical Sciences Birkbeck University of London UK

Neuro-symbolic systems combine neural perception and logical reasoning, representing one of the priorities of AI research. End-to-end learning of neuro-symbolic systems is highly desirable, but remains to be challenging. Resembling the distinction and cooperation between System 1 and System 2 of human thought (à la Kahneman), this paper proposes a framework that fuses neural network training, symbol grounding, and logical constraint synthesis to support learning in a weakly supervised setting. Technically, it is cast as a game with two optimization problems which correspond to neural network learning and symbolic constraint learning respectively. Such a formulation naturally embeds symbol grounding and enables the interaction between the neural and the symbolic part in both training and inference. The logical constraints are represented as cardinality constraints, and we use the trust region method to avoid degeneracy in learning. A distinguished feature of the optimization lies in the Boolean constraints for which we introduce a difference-of-convex programming approach. Both theoretical analysis and empirical evaluations substantiate the effectiveness of the proposed framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Subgraph-Oriented Heterogeneous Drug-Target Interaction Identification

Subgraph-Oriented Heterogeneous Drug-Target Interaction Iden...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaofeng Zhang Zeyu Huang Jun Bai Wenge Rong Yuanxin Ouyang Zhang Xiong State Key Laboratory of Software Development Environment Beihang University Beijing China Sino-French Engineer School Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

Drug-target interaction (DTI) is an important task in drug discovery and drug repurposing. Currently, most methods utilizing drug-based and protein-based similarity values to predict DTIs achieve promising results. However, calculating similarities for each pair of nodes is time-consuming, especially for relatively large datasets. In this research, we propose a novel subgraph-oriented heterogeneous DTI identification method that transforms the DTI task from a link prediction task to a subgraph classification task. For each link, a local subgraph around this link is extracted. Then, a subgraph labeling process distinguishes different topologies of subgraphs. A random walk-based node representation generation is also integrated with the model. Finally, we apply a graph neural network for the subgraph classification. Our method avoids incorporating human-made similarity values by extracting more meaningful local subgraph topological information. Experimental studies for known DTI predictions on two DTI datasets show promising results for DTI prediction. Empirical results for new DTI predictions on two external public databases show the generalization ability of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph-based Multi-view Clustering for Web services

Graph-based Multi-view Clustering for Web services

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Wang Yang Yuan Zhenzhen Kang Guosheng Cao Buqing Liu JianXun Xiao Yong HNUST Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China School of Computer Science and Engineering

The number of Web services on the Internet has been steadily increasing in recent years due to their growing popularity. Under the big data environment, how to effectively manage Web services is of significance for service discovery, service recommendation, etc. It is widely studied that Web services clustering is an effective way for service management. However, most of the current Web service clustering only extracts the information of Web services for clustering from one view, such as Web service content descriptions, networks in which Web services participate, and so on. Extracting information from Web services only unilaterally will not be able to provide a three-dimensional and comprehensive description of Web services, which may diminish the effect of Web service clustering. In addition, some Web service resources will be wasted if other information of Web services is not used at the same time. We find that multi-view clustering can simultaneously consider multiple information of a data at the same time, and multiple information can complement and enhance each other according to the characteristics of multiview clustering. Therefore, in this paper, we apply Web services to graph-based multi-view clustering in multi-view clustering to improve the performance of Web service clustering by simultaneously considering multiple feature information about Web services and distributing different weights to different information in the clustering process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Zhiyuan Wang Qingkai Meng Shan Zhang Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Institute of Artificial Intelligence Beihang University Beijing China State Key Laboratory of Software Development Environment

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform’s OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Efficient Packet Batching and Resource Allocation for GPU based NFV Acceleration

On Efficient Packet Batching and Resource Allocation for GPU...

引用

International Workshop on Quality of Service

作者： Deze Zeng Andong Zhu Lin Gu Quan Chen Minyi Guo School of Computer Science China University of Geosciences Wuhan Hubei China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

Network Function Virtualization (NFV) has already become an essential technology for improving the scalability and flexibility of modern computer networks. The performance gap has become the main issue that impedes the development of NFV. GPUs, with massive parallel processors, are advocated to accelerate the Virtualized Network Functions (VNFs). However, the special architecture and workflow of GPUs introduce new challenges, especially on the batched processing, and resource allocation. In this paper, we propose GPU-based NFV Acceleration framework (GNFA) with an efficient packet batching and resource allocation solution. Considering the increased latency caused by the accumulation of the GPU kernel invoking overhead, we first invent a latency reduction mechanism called SM Performance Compensation (SPC). A Partition and Adjustment based Batching and Resource Allocation (PABARA) algorithm that jointly considers batch size tuning and GPU thread allocation is also proposed. We have practically implemented GNFA and extensively evaluated its performance on some well-known VNFs. The experiment results show that GNFA can effectively promote the GPU resource utilization and improve the NFV performance in terms of per-packet latency.

关键词：

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：