检索结果-内蒙古大学图书馆

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Hui Yu Yu Zhang Ligang He Yingqi Zhao Xintao Li Ruida Xin Jin Zhao Xiaofei Liao Haikun Liu Bingsheng He Hai Jin National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Warwick United Kingdom National University of Singapore Singapore

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

Hypergraph Neural Network (HyperGNN) has emerged as a potent methodology for dissecting intricate multilateral connections among various entities. Current software/hardware solutions leverage a sequential execution model that relies on hyperedge and vertex indices for conducting standard matrix operations for HyperGNN inference. Yet, they are impeded by the dual challenges of redundant computation and irregular memory access overheads. This is primarily due to the frequent and repetitive access and updating of a number of feature vectors corresponding to the same hyperedges and vertices. To address these challenges, we propose the first redundancy-aware accelerator, RAHP, which enables high performance execution of HyperGNN inference. Specifically, we present a redundancy-aware asynchronous execution approach into the accelerator design for HyperGNN to reduce redundant computations and off-chip memory accesses. To unveil opportunities for data reuse and unlock the parallelism that existing HyperGNN solutions fail to capture, it prioritizes vertices with the highest degree as roots, prefetching other vertices along the hypergraph structure to capture the common vertices among multiple hyperedges, and synchronizing the computations of hyperedges and vertices in real-time. By such means, this facilitates the concurrent processing of relevant hyperedge and vertex computations of the common vertices along the hypergraph topology, resulting in smaller redundant computations overhead. Furthermore, by efficiently caching intermediate results of the common vertices, it curtails memory traffic and off-chip communications. To fully harness the performance potential of our proposed approach in the accelerator, RAHP incorporates a topology-driven data loading mechanism to minimize off-chip memory accesses on the fly. It is also endowed with an adaptive data synchronization scheme to mitigate the effects of conflicting updates of both hyperedges and vertices. Moreover, RAHP emplo

关键词： Computational modeling Neural networks Memory management Loading Energy conservation Vectors Software Topology Synchronization Standards

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of MPTCP ACK via alternative path in real network environment

Feasibility study of MPTCP ACK via alternative path in real ...

引用

2021 International Symposium on Grids and Cloud, ISGC 2021

作者： Koibuchi, Hiroyuki Abe, Hirotake Kato, Kazuhiko Graduate School of System and Information Engineering University of Tsukuba Japan Department of Computer Science University of Tsukuba Japan

Multi-path TCP (MPTCP) is a network protocol that has the potential to enhance network performance, which is crucial in grid computing systems to improve the overall system's performance. It utilizes multiple network paths between machines to achieve a high network performance. This protocol can also improve the connectivity of multiple servers that may be in different data centers by combining multiple network paths. One of the main issues of MPTCP is the path for ACK (acknowledgment) packets, which take the same path where original packets come from. When networks have different round trip times (RTTs), MPTCP may dispatch the ACK packet through a longer path, which is inefficient. HayACK solves this issue by selecting the path with the least RTTs. However, HayACK may suffer from inconsistent packets because of middleboxes, which are intermediary devices between the source and the destination that process network packets. These middleboxes may discard MPTCP packets because of inconsistent sequence numbers of HayACK packets, which is a product of HayACK's path selection. This study aims to investigate the usefulness of HayACK for high-performance data transfer when using multiple paths in real network environments and the influence of middleboxes on HayACK. Our investigation was conducted using various network paths by preparing many client hosts with different IP addresses and one server. The influence of middleboxes is determined by checking the probe packets passed through, changed, or discarded. Assuming the HayACK response, we crafted packets such as TCP SYN packets and TCP ACK packets. © Copyright owned by the author(s) under the terms of the Creative Commons

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

Augmented Educators and AI: Shaping the Future of Human-AI Collaboration in Learning

Augmented Educators and AI: Shaping the Future of Human-AI C...

引用

2025 CHI Conference on Human Factors in Computing systems, CHI EA 2025

作者： Kim, Hyeji Park, Jongyoul Jeon, Hyeongbae Fels, Sidney S. Dodson, Samuel Seo, Kyoungwon AI Convergence and Open Sharing System Seoul National University of Science and Technology Seoul South Korea Department of Applied Artificial Intelligence Seoul National University of Science and Technology Seoul South Korea TutorusLabs Daejeon South Korea Department of Electrical and Computer Engineering University of British Columbia Vancouver BC Canada Department of Information Science University at Buffalo Buffalo NY United States

ISBN: (纸本)9798400713958

As Artificial Intelligence (AI) becomes more deeply embedded in educational settings, it is crucial to explore how it can enhance—rather than replace—the role of educators. This workshop focuses on advancing AI-driven tools that support personalized learning and designing AI systems capable of understanding students’ emotional and cognitive needs. The workshop will explore two main themes: (1) empowering teachers with AI technologies for delivering customized feedback and individualized instruction, and (2) examining ethical and practical considerations for developing empathetic AI that complements the human aspects of teaching. Participants will discuss opportunities and challenges in building effective AI-augmented learning environments, considering ethical concerns such as privacy, equity, and the maintenance of human agency. The workshop aims to unite educators, researchers, and technologists in developing innovative solutions and fostering interdisciplinary dialogue. Key outcomes include establishing best practices for AI integration in education and disseminating research findings that shape the future of human-AI collaboration in teaching. © 2025 Copyright held by the owner/author(s).

关键词： Augmented Educators Empathetic AI Human-AI Collaboration

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

Evaluating the Performance to Detecting Topic Shift of Large...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

Congress on Evolutionary Computation

作者： Xunfeng Wu Songbai Liu Junkai Ji Lijia Ma Victor C. M. Leung College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases.

关键词： Training Heuristic algorithms Computational modeling Sociology Clustering algorithms Evolutionary computation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting

arXiv

引用

arXiv 2025年

作者： Wang, Weiyan Shi, Xingjian Shu, Ruiqi Gao, Yuan Chen, Rui Ray Wang, Kun Xu, Fan Xue, Jinbao Li, Shuaipeng Tao, Yangyu Wang, Di Wu, Hao Huang, Xiaomeng TEG Tencent China Boson AI United States Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University China Institute for Interdisciplinary Information Sciences Tsinghua University China School of Computer Science and Engineering Nanyang Technological University Singapore Department and Computer and Science University of Science and Technology of China China

In practice, physical spatiotemporal forecasting can suffer from data scarcity, because collecting large-scale data is non-trivial, especially for extreme events. Hence, we propose BeamVQ, a novel probabilistic framework to realize iterative self-training with new self-ensemble strategies, achieving better physical consistency and generalization on extreme events. Following any base forecasting model, we can encode its deterministic outputs into a latent space and retrieve multiple codebook entries to generate probabilistic outputs. Then BeamVQ extends the beam search from discrete spaces to the continuous state spaces in this field. We can further employ domain-specific metrics (e.g., Critical Success Index for extreme events) to filter out the top-k candidates and develop the new self-ensemble strategy by combining the high-quality candidates. The self-ensemble can not only improve the inference quality and robustness but also iteratively augment the training datasets during continuous self-training. Consequently, BeamVQ realizes the exploration of rare but critical phenomena beyond the original dataset. Comprehensive experiments on different benchmarks and backbones show that BeamVQ consistently reduces forecasting MSE (up to 39%), enhancing extreme events detection and proving its effectiveness in handling data scarcity. Our codes are available at https://***/easylearningscores/BeamVQ. © 2025, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Large Language Models for Sentiment Classification of AI-Related Tweets

Fine-Tuning Large Language Models for Sentiment Classificati...

引用

IEEE International WIE Conference on Electrical and computer engineering (WIECON-ECE)

作者： Md Jahid Alam Riad Rahul Debnath Mahfuzur Rahman Shuvo Fateha Jannat Ayrin Nobanul Hasan Ayesha Akhter Tamanna Prosenjit Roy Master Of Science In Information Technology (MSIT) Washington University of Science and Technology Department of Computer Science Prairie View A & M University Texas United States Department of Management Information System International American University Los Angeles California Department of Computer Science and Engineering Chittagong University (CU) Department of CSSE University Of AIUB

ISBN: (数字)9798331535476

ISBN: (纸本)9798331535483

Fine-tuning large language models (LLMs) for sentiment analysis presents a promising avenue for enhancing the understanding of public sentiment surrounding artificial intelligence (AI) topics. This study explores the fine-tuning of Large Language Models (LLMs) for sentiment analysis on AI-related topics using social media data. We collected approximately 20,000 tweets containing hashtags and comments related to AI concerns, including ‘AI Danger,’ ‘AI Ethics,’ ‘AI Problems,’ ‘AI Creating Problem on Jobs,’ and ‘AI Threat.’ The dataset captures public sentiment surrounding potential negative impacts of artificial intelligence. Three cutting-edge LLMs, Llama 2, Gemma, Mistral, and Phi 3, served as our foundational models for fine-tuning. To enhance model performance, we implemented advanced prompt engineering techniques, including Chain-of-Thought (COT), Algorithm-of-Thoughts (AOT), Fewshot and EmotionPrompt. Our results demonstrate that Llama 2 achieves consistent performance across all techniques with accuracies ranging from 82.3% to 83.9%. Phi-3 showed the best performance with EmotionPrompt and Fewshot techniques, achieving accuracies of 87.8% and 87.4% respectively. Gemma 7B performed optimally with Fewshot at 84.0% accuracy, while Mistral achieved 85.0% accuracy using the same technique. The research reveals that Fewshot and AOT consistently produce reliable results across models, with Emotion-Prompt showing model-specific effectiveness. Our findings have applications for enhancing the precision and dependability of sentiment analysis instruments that track public opinion and AI-related speech.

关键词： Sentiment analysis Ethics Accuracy Social networking (online) Large language models Computational modeling Instruments Speech enhancement Reliability Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis in Indonesian Trading using Lexicon-based and Support Vector Machine

Sentiment Analysis in Indonesian Trading using Lexicon-based...

引用

computer science, Information Technology and engineering (ICCoSITE), International Conference on

作者： Raymond Sunardi Oetama Yanfi Yanfi Masagus M. Ikhsan Assiddiq U.P Sani Muhamad Isa Information System DepartmentFaculty of Engineering and Informatics Universitas Multimedia Nusantara Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

Many individuals now trade online utilizing trading software in the digital world. Binomo is one of Indonesia's most popular trading platforms. This is because some influencers made several promises to Binomo customers. Since many customers were deceived, this case became quite popular. This study was executed to see how Indonesians felt about the Binomo application after the case went viral. The solution taken was in the form of sentiment analysis because there had been no previous research on sentiment analysis that discussed the Binomo case. The data was scanned using Netlytic tools, a cloud-based text and social network analyzer capable of identifying any talks on social media sites such as Twitter. The sentiment analysis of Binomo trading tweets by using the Multi-Perspective Question Answering lexicon utilized the KNIME tool. But unfortunately, the accuracy of sentiment analysis results is low. Furthermore, the Support Vector Machine technique is also being conducted. The Term Frequency-Inverse Document Frequency method is applied to perform feature extraction whilst the chi-square approach is utilized to identify features that are thought to be useful for inclusion in the classification process and to exclude features that are irrelevant to the target class. The obtained accuracy is 86%. The study proposes that words from the algorithm's outputs can be utilized to improve the quality of sentiment analysis using the lexicon. As an outcome of the algorithm, positive and negative terms are added to the lexicon, increasing the accuracy of sentiment analysis using the new vocabulary from 58.984% to 71.146%.

关键词： Support vector machines Training Sentiment analysis Vocabulary Dictionaries Social networking (online) Blogs

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Arabic Text Summarization Techniques: Evaluating Word Frequency, K-Means Clustering, and PageRank Algorithm

A Comparative Analysis of Arabic Text Summarization Techniqu...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Abdelrhman A. Karim Manar A. Ibrahim Mahmoud M. Hosny Abdulrhman H. Ibrahim Reem A. Mohamed Magy Elbanbawy Aya M. Al-Zoghby Khaled Foad Ibrahim Fathy Moawad Artificial Intelligence Engineering Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Artificial Intelligence Science Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Computer and System Department Faculty of Engineering Mansoura University Dakhlia Egypt Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Computer Science Department Faculty of Computers and Artificial Intelligence Damietta University Damietta Egypt Information Systems Faculty of Computers and Artificial Intelligence Benha University Egypt Information Systems Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Department of Artificial Intelligence College of Computer Science and Engineering Taibah University Medina Saudi Arabia

ISBN: (数字)9798350367775

ISBN: (纸本)9798350367782

This study explores methods to efficiently summarize extensive Arabic texts, addressing the growing need to condense large volumes of content across various fields. Three primary techniques are evaluated: Word Frequency Analysis, K-means Clustering based on Sentence Proximity, and the PageRank Algorithm. The research finds the PageRank Algorithm to be the most effective, delivering higher compression ratios while maintaining strong recall and precision metrics. In particular, the PageRank method achieved the highest compression ratio of 0.562 while maintaining a population standard deviation of 2.0, compared to other techniques. Evaluation metrics such as population standard deviation, F1 score, and compression ratio support these findings. The study also examines advanced approaches like fuzzy logic-based methods, transformers, and multi-document summarization, aiming to enhance Arabic text summarization.

关键词： Measurement Clustering algorithms Text summarization Ubiquitous computing Transformers Information retrieval Data mining Standards

来源：评论

学校读者我要写书评

暂无评论

Iterative Feature Space Optimization through Incremental Adaptive Evaluation

arXiv

引用

arXiv 2025年

作者： Wu, Yanping Huang, Yanyong Chen, Zhengzhang Yao, Zijun Fu, Yanjie Liu, Kunpeng Luo, Xiao Wang, Dongjie University of Kansas Department of Electrical Engineering and Computer Science United States Southwestern University of Finance and Economics Department of Statistics China NEC Laboratories America Data Science and System Security United States Arizona State University Department of Computing and Augmented Intelligence United States Portland State University Department of Computer Science United States University of California Los Angeles Department of Computer Science United States

Iterative feature space optimization involves systematically evaluating and adjusting the feature space to improve downstream task performance. However, existing works suffer from three key limitations: 1) overlooking differences among data samples leads to evaluation bias;2) tailoring feature spaces to specific machine learning models results in overfitting and poor generalization;3) requiring the evaluator to be retrained from scratch during each optimization iteration significantly reduces the overall efficiency of the optimization process. To bridge these gaps, we propose a gEneralized Adaptive feature Space Evaluator (EASE) to efficiently produce optimal and generalized feature spaces. This framework consists of two key components: Feature-Sample Subspace Generator and Contextual Attention Evaluator. The first component aims to decouple the information distribution within the feature space to mitigate evaluation bias. To achieve this, we first identify features most relevant to prediction tasks and samples most challenging for evaluation based on feedback from the subsequent evaluator. These identified feature and samples are then used to construct feature subspaces for next optimization iteration. This decoupling strategy makes the evaluator consistently target the most challenging aspects of the feature space. The second component intends to incrementally capture evolving patterns of the feature space for efficient evaluation. We propose a weighted-sharing multi-head attention mechanism to encode key characteristics of the feature space into an embedding vector for evaluation. Moreover, the evaluator is updated incrementally, retaining prior evaluation knowledge while incorporating new insights, as consecutive feature spaces during the optimization process share partial information. Extensive experiments on fourteen real-world datasets demonstrate the effectiveness of the proposed framework. Our code and data are publicly available Copyright © 2025, The Autho

关键词： Vector spaces

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：